NIPS 2018 收录论文及下载链接

• Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization Francis Bach
• Structure-Aware Convolutional Neural Networks Jianlong Chang, Jie Gu, Lingfeng Wang, GAOFENG MENG, SHIMING XIANG, Chunhong Pan
• Kalman Normalization: Normalizing Internal Representations Across Network Layers Guangrun Wang, jiefeng peng, Ping Luo, Xinjiang Wang, Liang Lin
• HOGWILD!-Gibbs can be PanAccurate Constantinos Daskalakis, Nishanth Dikkala, Siddhartha Jayanti
• Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language Seonghyeon Nam, Yunji Kim, Seon Joo Kim
• IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis Huaibo Huang, zhihang li, Ran He, Zhenan Sun, Tieniu Tan
• Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with \beta-Divergences Jeremias Knoblauch, Jack E. Jewson, Theodoros Damoulas
• Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning Tyler Scott, Karl Ridgeway, Michael C. Mozer
• Generalized Inverse Optimization through Online Learning Chaosheng Dong, Yiran Chen, Bo Zeng
• An Off-policy Policy Gradient Theorem Using Emphatic Weightings Ehsan Imani, Eric Graves, Martha White
• Supervised autoencoders: Improving generalization performance with unsupervised regularizers Lei Le, Andrew Patterson, Martha White
• Visual Object Networks: Image Generation with Disentangled 3D Representations Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu, Antonio Torralba, Josh Tenenbaum, Bill Freeman
• Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units Yixi Xu, Xiao Wang
• Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems Mrinmaya Sachan, Kumar Avinava Dubey, Tom M. Mitchell, Dan Roth, Eric P. Xing
• Learning long-range spatial dependencies with horizontal gated recurrent units Drew Linsley, Junkyung Kim, Vijay Veerabadran, Charles Windolf, Thomas Serre
• Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution Zhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, Chao Zhang
• Fast Similarity Search via Optimal Sparse Lifting Wenye Li, Jingwei Mao, Yin Zhang, Shuguang Cui
• Learning Deep Disentangled Embeddings With the F-Statistic Loss Karl Ridgeway, Michael C. Mozer
• Geometrically Coupled Monte Carlo Sampling Mark Rowland, Krzysztof M. Choromanski, François Chalus, Aldo Pacchiano, Tamas Sarlos, Richard E. Turner, Adrian Weller
• Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation Siyuan Huang, Siyuan Qi, Yinxue Xiao, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu
• An Efficient Pruning Algorithm for Robust Isotonic Regression Cong Han Lim
• PAC-learning in the presence of adversaries Daniel Cullina, Arjun Nitin Bhagoji, Prateek Mittal
• Sparse DNNs with Improved Adversarial Robustness Yiwen Guo, Chao Zhang, Changshui Zhang, Yurong Chen
• Snap ML: A Hierarchical Framework for Machine Learning Celestine Dünner, Thomas Parnell, Dimitrios Sarigiannis, Nikolas Ioannou, Andreea Anghel, Gummadi Ravi, Madhusudanan Kandasamy, Haralampos Pozidis
• See and Think: Disentangling Semantic Scene Completion Shice Liu, YU HU, Yiming Zeng, Qiankun Tang, Beibei Jin, Yinhe Han, Xiaowei Li
• Chain of Reasoning for Visual Question Answering Chenfei Wu, Jinlai Liu, Xiaojie Wang, Xuan Dong
• Sigsoftmax: Reanalysis of the Softmax Bottleneck Sekitoshi Kanai, Yasuhiro Fujiwara, Yuki Yamanaka, Shuichi Adachi
• Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation Wenqi Ren, Jiawei Zhang, Lin Ma, Jinshan Pan, Xiaochun Cao, Wangmeng Zuo, Wei Liu, Ming-Hsuan Yang
• Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC Tolga Birdal, Umut Simsekli, Mustafa Onur Eken, Slobodan Ilic
• MetaAnchor: Learning to Detect Objects with Customized Anchors Tong Yang, Xiangyu Zhang, Zeming Li, Wenqiang Zhang, Jian Sun
• Image Inpainting via Generative Multi-column Convolutional Neural Networks Yi Wang, Xin Tao, Xiaojuan Qi, Xiaoyong Shen, Jiaya Jia
• On Misinformation Containment in Online Social Networks Amo Tong, Ding-Zhu Du, Weili Wu
• A^2-Nets: Double Attention Networks Yunpeng Chen, Yannis Kalantidis, Jianshu Li, Shuicheng Yan, Jiashi Feng
• Self-Supervised Generation of Spatial Audio for 360° Video Pedro Morgado, Nuno Nvasconcelos, Timothy Langlois, Oliver Wang
• How Many Samples are Needed to Estimate a Convolutional Neural Network? Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan R. Salakhutdinov, Aarti Singh
• Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced Simon S. Du, Wei Hu, Jason D. Lee
• Optimization for Approximate Submodularity Yaron Singer, Avinatan Hassidim
• (Probably) Concave Graph Matching Haggai Maron, Yaron Lipman
• Deep Defense: Training DNNs with Improved Adversarial Robustness Ziang Yan, Yiwen Guo, Changshui Zhang
• Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes Junqi Tang, Mohammad Golbabaee, Francis Bach, Mike E. davies
• Implicit Reparameterization Gradients Mikhail Figurnov, Shakir Mohamed, Andriy Mnih
• Training DNNs with Hybrid Block Floating Point Mario Drumond, Tao LIN, Martin Jaggi, Babak Falsafi
• A Model for Learned Bloom Filters and Optimizing by Sandwiching Michael Mitzenmacher
• Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis Haoye Dong, Xiaodan Liang, Ke Gong, Hanjiang Lai, Jia Zhu, Jian Yin
• Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions Minhyuk Sung, Hao Su, Ronald Yu, Leonidas J. Guibas
• Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal Modeling Yunzhe Tao, Qi Sun, Qiang Du, Wei Liu
• Are ResNets Provably Better than Linear Predictors? Ohad Shamir
• Learning to Decompose and Disentangle Representations for Video Prediction Jun-Ting Hsieh, Bingbin Liu, De-An Huang, Li F. Fei-Fei, Juan Carlos Niebles
• Multi-Task Learning as Multi-Objective Optimization Ozan Sener, Vladlen Koltun
• Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search Zhuwen Li, Qifeng Chen, Vladlen Koltun
• Self-Erasing Network for Integral Object Attention Qibin Hou, PengTao Jiang, Yunchao Wei, Ming-Ming Cheng
• LinkNet: Relational Embedding for Scene Graph Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
• How to Start Training: The Effect of Initialization and Architecture Boris Hanin, David Rolnick
• Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients? Boris Hanin
• Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives Amit Dhurandhar, Pin-Yu Chen, Ronny Luss, Chun-Chen Tu, Paishun Ting, Karthikeyan Shanmugam, Payel Das
• HitNet: Hybrid Ternary Recurrent Neural Network Peiqi Wang, Xinfeng Xie, Lei Deng, Guoqi Li, Dongsheng Wang, Yuan Xie
• A Unified Framework for Extensive-Form Game Abstraction with Bounds Christian Kroer, Tuomas Sandholm
• Removing the Feature Correlation Effect of Multiplicative Noise Zijun Zhang, Yining Zhang, Zongpeng Li
• Maximum-Entropy Fine Grained Classification Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, Nikhil Naik
• On Learning Markov Chains Yi HAO, Alon Orlitsky, Venkatadheeraj Pichapati
• A Neural Compositional Paradigm for Image Captioning Bo Dai, Sanja Fidler, Dahua Lin
• Quantifying Learning Guarantees for Convex but Inconsistent Surrogates Kirill Struminsky, Simon Lacoste-Julien, Anton Osokin
• Dialog-based Interactive Image Retrieval Xiaoxiao Guo, Hui Wu, Yu Cheng, Steven Rennie, Gerald Tesauro, Rogerio Feris
• SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang
• Are GANs Created Equal? A Large-Scale Study Mario Lucic, Karol Kurach, Marcin Michalski, Sylvain Gelly, Olivier Bousquet
• Learning Disentangled Joint Continuous and Discrete Representations Emilien Dupont
• TADAM: Task dependent adaptive metric for improved few-shot learning Boris Oreshkin, Pau Rodríguez López, Alexandre Lacoste
• Do Less, Get More: Streaming Submodular Maximization with Subsampling Moran Feldman, Amin Karbasi, Ehsan Kazemi
• Deep Neural Nets with Interpolating Function as Output Activation Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley Osher
• FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction Shuyang Sun, Jiangmiao Pang, Jianping Shi, Shuai Yi, Wanli Ouyang
• Visual Memory for Robust Path Following Ashish Kumar, Saurabh Gupta, David Fouhey, Sergey Levine, Jitendra Malik
• KDGAN: Knowledge Distillation with Generative Adversarial Networks Xiaojie Wang, Rui Zhang, Yu Sun, Jianzhong Qi
• Long short-term memory and Learning-to-learn in networks of spiking neurons Guillaume Bellec, Darjan Salaj, Anand Subramoney, Robert Legenstein, Wolfgang Maass
• Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN Shupeng Su, Chao Zhang, Kai Han, Yonghong Tian
• Informative Features for Model Comparison Wittawat Jitkrittum, Heishiro Kanagawa, Patsorn Sangkloy, James Hays, Bernhard Schölkopf, Arthur Gretton
• PointCNN: Convolution On X-Transformed Points Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen
• Connectionist Temporal Classification with Maximum Entropy Regularization Hu Liu, Sheng Jin, Changshui Zhang
• Large Margin Deep Networks for Classification Gamaleldin Elsayed, Dilip Krishnan, Hossein Mobahi, Kevin Regan, Samy Bengio
• Generalizing Graph Matching beyond Quadratic Assignment Model Tianshu Yu, Junchi Yan, Yilin Wang, Wei Liu, baoxin Li
• Solving Large Sequential Games with the Excessive Gap Technique Christian Kroer, Gabriele Farina, Tuomas Sandholm
• Discrimination-aware Channel Pruning for Deep Neural Networks Zhuangwei Zhuang, Mingkui Tan, Bohan Zhuang, Jing Liu, Yong Guo, Qingyao Wu, Junzhou Huang, Jinhui Zhu
• On the Dimensionality of Word Embedding Zi Yin, Yuanyuan Shen
• Reinforced Continual Learning Ju Xu, Zhanxing Zhu
• Uncertainty-Aware Attention for Reliable Interpretation and Prediction Jay Heo, Hae Beom Lee, Saehoon Kim, Juho Lee, Kwang Joon Kim, Eunho Yang, Sung Ju Hwang
• DropMax: Adaptive Variational Softmax Hae Beom Lee, Juho Lee, Saehoon Kim, Eunho Yang, Sung Ju Hwang
• Posterior Concentration for Sparse Deep Learning Veronika Rockova, nicholas polson
• A flexible model for training action localization with varying levels of supervision Guilhem Chéron, Jean-Baptiste Alayrac, Ivan Laptev, Cordelia Schmid
• A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents YAN ZHENG, Zhaopeng Meng, Jianye Hao, Zongzhang Zhang, Tianpei Yang, Changjie Fan
• Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited Di Wang, Marco Gaboardi, Jinhui Xu
• Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks Hang Gao, Zheng Shou, Alireza Zareian, Hanwang Zhang, Shih-Fu Chang
• Learning semantic similarity in a continuous space Michel Deudon
• MetaReg: Towards Domain Generalization using Meta-Regularization Yogesh Balaji, Swami Sankaranarayanan, Rama Chellappa
• Boosted Sparse and Low-Rank Tensor Regression Lifang He, Kun Chen, Wanwan Xu, Jiayu Zhou, Fei Wang
• Domain-Invariant Projection Learning for Zero-Shot Recognition An Zhao, Mingyu Ding, Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen
• Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding Kexin Yi, Jiajun Wu, Chuang Gan, Antonio Torralba, Pushmeet Kohli, Josh Tenenbaum
• Frequency-Domain Dynamic Pruning for Convolutional Neural Networks Zhenhua Liu, Jizheng Xu, Xiulian Peng, Ruiqin Xiong
• Quadratic Decomposable Submodular Function Minimization Pan Li, Niao He, Olgica Milenkovic
• A Block Coordinate Ascent Algorithm for Mean-Variance Optimization Tengyang Xie, Bo Liu, Yangyang Xu, Mohammad Ghavamzadeh, Yinlam Chow, Daoming Lyu, Daesub Yoon
• \ell_1-regression with Heavy-tailed Distributions Lijun Zhang, Zhi-Hua Zhou
• Neural Nearest Neighbors Networks Tobias Plötz, Stefan Roth
• Efficient nonmyopic batch active search Shali Jiang, Gustavo Malkomes, Matthew Abbott, Benjamin Moseley, Roman Garnett
• A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers Omer Ben-Porat, Moshe Tennenholtz
• Interactive Structure Learning with Structural Query-by-Committee Christopher Tosh, Sanjoy Dasgupta
• Global Geometry of Multichannel Sparse Blind Deconvolution on the Sphere Yanjun Li, Yoram Bresler
• Video-to-Video Synthesis Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Guilin Liu, Andrew Tao, Jan Kautz, Bryan Catanzaro
• How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD Zeyuan Allen-Zhu
• Synthesized Policies for Transfer and Adaptation across Tasks and Environments Hexiang Hu, Liyu Chen, Boqing Gong, Fei Sha
• Adversarial vulnerability for any classifier Alhussein Fawzi, Hamza Fawzi, Omar Fawzi
• Evolution-Guided Policy Gradient in Reinforcement Learning Shauharda Khadka, Kagan Tumer
• Toddler-Inspired Visual Object Learning Sven Bambach, David Crandall, Linda Smith, Chen Yu
• Alternating optimization of decision trees, with application to learning sparse oblique trees Miguel A. Carreira-Perpinan, Pooya Tavallali
• FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, hongsheng Li
• New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity Pan Zhou, Xiaotong Yuan, Jiashi Feng
• The Lingering of Gradients: How to Reuse Gradients Over Time Zeyuan Allen-Zhu, David Simchi-Levi, Xinshang Wang
• Unsupervised Learning of View-invariant Action Representations Junnan Li, Yongkang Wong, Qi Zhao, Mohan Kankanhalli
• Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making Hoda Heidari, Claudio Ferrari, Krishna Gummadi, Andreas Krause
• Global Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural Networks Qilong Wang, Zilin Gao, Jiangtao Xie, Wangmeng Zuo, Peihua Li
• Image-to-image translation for cross-domain disentanglement Abel Gonzalez-Garcia, Joost van de Weijer, Yoshua Bengio
• Gradient Sparsification for Communication-Efficient Distributed Optimization Jianqiao Wangni, Jialei Wang, Ji Liu, Tong Zhang
• Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection Taylor Mordan, Nicolas THOME, Gilles Henaff, Matthieu Cord
• Adaptive Online Learning in Dynamic Environments Lijun Zhang, Shiyin Lu, Zhi-Hua Zhou
• FRAGE: Frequency-Agnostic Word Representation Chengyue Gong, Di He, Xu Tan, Tao Qin, Liwei Wang, Tie-Yan Liu
• Generative Neural Machine Translation Harshil Shah, David Barber
• Found Graph Data and Planted Vertex Covers Austin R. Benson, Jon Kleinberg
• Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding Hajin Shim, Sung Ju Hwang, Eunho Yang
• Regularization Learning Networks: Deep Learning for Tabular Datasets Ira Shavitt, Eran Segal
• Multitask Boosting for Survival Analysis with Competing Risks Alexis Bellot, Mihaela van der Schaar
• Geometry Based Data Generation Ofir Lindenbaum, Jay Stanley, Guy Wolf, Smita Krishnaswamy
• SLAYER: Spike Layer Error Reassignment in Time Sumit Bam Shrestha, Garrick Orchard
• On Oracle-Efficient PAC RL with Rich Observations Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
• Gradient Descent for Spiking Neural Networks Dongsung Huh, Terrence J. Sejnowski
• Generalizing Tree Probability Estimation via Bayesian Networks Cheng Zhang, Frederick A Matsen IV
• Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior Sid Reddy, Anca Dragan, Sergey Levine
• Designing by Training: Acceleration Neural Network for Fast High-Dimensional Convolution Longquan Dai, Liang Tang, Yuan Xie, Jinhui Tang
• Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners Yuxin Chen, Adish Singla, Oisin Mac Aodha, Pietro Perona, Yisong Yue
• A loss framework for calibrated anomaly detection
• PacGAN: The power of two samples in generative adversarial networks Zinan Lin, Ashish Khetan, Giulia Fanti, Sewoong Oh
• Variational Memory Encoder-Decoder Hung Le, Truyen Tran, Thin Nguyen, Svetha Venkatesh
• Stochastic Composite Mirror Descent: Optimal Bounds with High Probabilities Yunwen Lei, Ke Tang
• Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation Yuan Li, Xiaodan Liang, Zhiting Hu, Eric P. Xing
• Overcoming Language Priors in Visual Question Answering with Adversarial Regularization Sainandan Ramakrishnan, Aishwarya Agrawal, Stefan Lee
• Hybrid Knowledge Routed Modules for Large-scale Object Detection ChenHan Jiang, Hang Xu, Xiaodan Liang, Liang Lin
• Bilinear Attention Networks Jin-Hwa Kim, Jaehyun Jun, Byoung-Tak Zhang
• Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning Xing Yan, Weizhong Zhang, Lin Ma, Wei Liu, Qi Wu
• Multi-Class Learning: From Theory to Algorithm Jian Li, Yong Liu, Rong Yin, Hua Zhang, Lizhong Ding, Weiping Wang
• Multivariate Time Series Imputation with Generative Adversarial Networks Yonghong Luo, Xiangrui Cai, Ying ZHANG, Jun Xu, Yuan xiaojie
• Learning Versatile Filters for Efficient Convolutional Neural Networks Yunhe Wang, Chang Xu, Chunjing XU, Chao Xu, Dacheng Tao
• Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization Robert Gower, Filip Hanzely, Peter Richtarik, Sebastian U. Stich
• DifNet: Semantic Segmentation by Diffusion Networks Peng Jiang, Fanglin Gu, Yunhai Wang, Changhe Tu, Baoquan Chen
• Conditional Adversarial Domain Adaptation Mingsheng Long, ZHANGJIE CAO, Jianmin Wang, Michael I. Jordan
• Neighbourhood Consensus Networks Ignacio Rocco, Mircea Cimpoi, Relja Arandjelović, Akihiko Torii, Tomas Pajdla, Josef Sivic
• Relating Leverage Scores and Density using Regularized Christoffel Functions Edouard Pauwels, Francis Bach, Jean-Philippe Vert
• Non-Local Recurrent Network for Image Restoration Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, Thomas S. Huang
• Bayesian Semi-supervised Learning with Graph Gaussian Processes Yin Cheng Ng, Nicolò Colombo, Ricardo Silva
• Foreground Clustering for Joint Segmentation and Localization in Videos and Images Abhishek Sharma
• Video Prediction via Selective Sampling Jingwei Xu, Bingbing Ni, Xiaokang Yang
• Distilled Wasserstein Learning for Word Embedding and Topic Modeling Hongteng Xu, Wenlin Wang, Wei Liu, Lawrence Carin
• Learning to Exploit Stability for 3D Scene Parsing Yilun Du, Zhijian Liu, Hector Basevi, Ales Leonardis, Bill Freeman, Josh Tenenbaum, Jiajun Wu
• Neural Guided Constraint Logic Programming for Program Synthesis Lisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William Byrd, Matthew Might, Raquel Urtasun, Richard Zemel
• Genetic-Gated Networks for Deep Reinforcement Learning Simyung Chang, John Yang, Jaeseok Choi, Nojun Kwak
• Fighting Boredom in Recommender Systems with Linear Reinforcement Learning Romain WARLOP, Alessandro Lazaric, Jérémie Mary
• Enhancing the Accuracy and Fairness of Human Decision Making Isabel Valera, Adish Singla, Manuel Gomez Rodriguez
• Temporal Regularization for Markov Decision Process Pierre Thodoroff, Audrey Durand, Joelle Pineau, Doina Precup
• The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning Jesse Krijthe, Marco Loog
• Simple random search of static linear policies is competitive for reinforcement learning Horia Mania, Aurelia Guy, Benjamin Recht
• Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization Yizhe Zhang, Michel Galley, Jianfeng Gao, Zhe Gan, Xiujun Li, Chris Brockett, Bill Dolan
• Entropy and mutual information in models of deep neural networks Marylou Gabrié, Andre Manoel, Clément Luneau, jean barbier, Nicolas Macris, Florent Krzakala, Lenka Zdeborová
• Collaborative Learning for Deep Neural Networks Guocong Song, Wei Chai
• High Dimensional Linear Regression using Lattice Basis Reduction Ilias Zadik, David Gamarnik
• Symbolic Graph Reasoning Meets Convolutions Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P. Xing
• DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors Arash Vahdat, Evgeny Andriyash, William Macready
• Partially-Supervised Image Captioning Peter Anderson, Stephen Gould, Mark Johnson
• 3D-Aware Scene Manipulation via Inverse Graphics Shunyu Yao, Tzu Ming Hsu, Jun-Yan Zhu, Jiajun Wu, Antonio Torralba, Bill Freeman, Josh Tenenbaum
• Random Feature Stein Discrepancies Jonathan Huggins, Lester Mackey
• Distributed Stochastic Optimization via Adaptive SGD Ashok Cutkosky, Róbert Busa-Fekete
• Precision and Recall for Time Series Nesime Tatbul, Tae Jun Lee, Stan Zdonik, Mejbah Alam, Justin Gottschlich
• Deep Attentive Tracking via Reciprocative Learning Shi Pu, Yibing Song, Chao Ma, Honggang Zhang, Ming-Hsuan Yang
• Virtual Class Enhanced Discriminative Embedding Learning Binghui Chen, Weihong Deng, Haifeng Shen
• Attention in Convolutional LSTM for Gesture Recognition Liang Zhang, Guangming Zhu, Lin Mei, Peiyi Shen, Syed Afaq Ali Shah, Mohammed Bennamoun
• Pelee: A Real-Time Object Detection System on Mobile Devices Robert J. Wang, Xiang Li, Charles X. Ling
• Universal Growth in Production Economies Simina Branzei, Ruta Mehta, Noam Nisan
• Bayesian Model Selection Approach to Boundary Detection with Non-Local Priors Fei Jiang, Guosheng Yin, Francesca Dominici
• Efficient Stochastic Gradient Hard Thresholding Pan Zhou, Xiaotong Yuan, Jiashi Feng
• SplineNets: Continuous Neural Decision Graphs Cem Keskin, Shahram Izadi
• Generalized Zero-Shot Learning with Deep Calibration Network Shichen Liu, Mingsheng Long, Jianmin Wang, Michael I. Jordan
• Neural Architecture Search with Bayesian Optimisation and Optimal Transport Kirthevasan Kandasamy, Willie Neiswanger, Jeff Schneider, Barnabas Poczos, Eric P. Xing
• Embedding Logical Queries on Knowledge Graphs Will Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, Jure Leskovec
• Learning Optimal Reserve Price against Non-myopic Bidders Jinyan Liu, Zhiyi Huang, Xiangning Wang
• Sequential Context Encoding for Duplicate Removal Lu Qi, Shu Liu, Jianping Shi, Jiaya Jia
• Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning Supasorn Suwajanakorn, Noah Snavely, Jonathan J. Tompson, Mohammad Norouzi
• Nonparametric learning from Bayesian models with randomized objective functions Simon Lyddon, Stephen Walker, Chris C. Holmes
• SEGA: Variance Reduction via Gradient Sketching Filip Hanzely, Konstantin Mishchenko, Peter Richtarik
• Automatic Program Synthesis of Long Programs with a Learned Garbage Collector Amit Zohar, Lior Wolf
• One-Shot Unsupervised Cross Domain Translation Sagie Benaim, Lior Wolf
• Regularizing by the Variance of the Activations' Sample-Variances Etai Littwin, Lior Wolf
• Overlapping Clustering Models, and One (class) SVM to Bind Them All Xueyu Mao, Purnamrita Sarkar, Deepayan Chakrabarti
• Algorithmic Linearly Constrained Gaussian Processes Markus Lange-Hegermann
• DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning Runsheng Yu, Wenyu Liu, Yasen Zhang, Zhi Qu, Deli Zhao, Bo Zhang
• Norm matters: efficient and accurate normalization schemes in deep networks Elad Hoffer, Ron Banner, Itay Golan, Daniel Soudry
• Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms Zhihui Zhu, Yifan Wang, Daniel Robinson, Daniel Naiman, Rene Vidal, Manolis Tsakiris
• MULAN: A Blind and Off-Grid Method for Multichannel Echo Retrieval Helena Peic Tukuljac, Antoine Deleforge, Remi Gribonval
• Mixture Matrix Completion Daniel Pimentel-Alarcon
• Trajectory Convolution for Action Recognition Yue Zhao, Yuanjun Xiong, Dahua Lin
• The Description Length of Deep Learning models Léonard Blier, Yann Ollivier
• A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem Sampath Kannan, Jamie H. Morgenstern, Aaron Roth, Bo Waggoner, Zhiwei Steven Wu
• Revisiting Decomposable Submodular Function Minimization with Incidence Relations Pan Li, Olgica Milenkovic
• A Practical Algorithm for Distributed Clustering and Outlier Detection Jiecao Chen, Erfan Sadeqi Azer, Qin Zhang
• Learning to Reconstruct Shapes from Unseen Classes Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Josh Tenenbaum, Bill Freeman, Jiajun Wu
• BourGAN: Generative Networks with Metric Embeddings Chang Xiao, Peilin Zhong, Changxi Zheng
• Smoothed analysis of the low-rank approach for smooth semidefinite programs Thomas Pumir, Samy Jelassi, Nicolas Boumal
• Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning Ofir Marom, Benjamin Rosman
• Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate Mikhail Belkin, Daniel J. Hsu, Partha Mitra
• Breaking the Span Assumption Yields Fast Finite-Sum Minimization Robert Hannah, Yanli Liu, Daniel O'Connor, Wotao Yin
• Structured Local Minima in Sparse Blind Deconvolution Yuqian Zhang, Han-wen Kuo, John Wright
• GIANT: Globally Improved Approximate Newton Method for Distributed Optimization Shusen Wang, Farbod Roosta-Khorasani, Peng Xu, Michael W. Mahoney
• Modelling sparsity, heterogeneity, reciprocity and community structure in temporal interaction data Xenia Miscouridou, Francois Caron, Yee Whye Teh
• Non-monotone Submodular Maximization in Exponentially Fewer Iterations Eric Balkanski, Adam Breuer, Yaron Singer
• MetaGAN: An Adversarial Approach to Few-Shot Learning Ruixiang ZHANG, Tong Che, Zoubin Ghahramani, Yoshua Bengio, Yangqiu Song
• Local Differential Privacy for Evolving Data Matthew Joseph, Aaron Roth, Jonathan Ullman, Bo Waggoner
• Gaussian Process Conditional Density Estimation Vincent Dutordoir, Hugh Salimbeni, James Hensman, Marc Deisenroth
• Meta-Gradient Reinforcement Learning Zhongwen Xu, Hado P. van Hasselt, David Silver
• Modular Networks: Learning to Decompose Neural Computation Louis Kirsch, Julius Kunze, David Barber
• Learning to Navigate in Cities Without a Map Piotr Mirowski, Matt Grimes, Mateusz Malinowski, Karl Moritz Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, koray kavukcuoglu, Andrew Zisserman, Raia Hadsell
• Query Complexity of Bayesian Private Learning Kuang Xu
• A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization Cedric Josz, Yi Ouyang, Richard Zhang, Javad Lavaei, Somayeh Sojoudi
• Recurrent World Models Facilitate Policy Evolution David Ha, Jürgen Schmidhuber
• Ridge Regression and Provable Deterministic Ridge Leverage Score Sampling Shannon McCurdy
• Wasserstein Variational Inference Luca Ambrogioni, Umut Güçlü, Yağmur Güçlütürk, Max Hinne, Marcel A. J. van Gerven, Eric Maris
• How Does Batch Normalization Help Optimization? Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas, Aleksander Madry
• Verifiable Reinforcement Learning via Policy Extraction Osbert Bastani, Yewen Pu, Armando Solar-Lezama
• Leveraged volume sampling for linear regression Michal Derezinski, Manfred K. Warmuth, Daniel J. Hsu
• Model Agnostic Supervised Local Explanations Gregory Plumb, Denali Molitor, Ameet S. Talwalkar
• A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication Peng Jiang, Gagan Agrawal
• Active Learning for Non-Parametric Regression Using Purely Random Trees Jack Goetz, Ambuj Tewari, Paul Zimmerman
• Tree-to-tree Neural Networks for Program Translation Xinyun Chen, Chang Liu, Dawn Song
• Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks Hyeonseob Nam, Hyo-Eun Kim
• Structural Causal Bandits: Where to Intervene? Sanghack Lee, Elias Bareinboim
• Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog Sang-Woo Lee, Yu-Jung Heo, Byoung-Tak Zhang
• A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation Alexander H. Liu, Yen-Cheng Liu, Yu-Ying Yeh, Yu-Chiang Frank Wang
• Online Learning with an Unknown Fairness Metric Stephen Gillen, Christopher Jung, Michael Kearns, Aaron Roth
• Isolating Sources of Disentanglement in Variational Autoencoders Tian Qi Chen, Xuechen Li, Roger B. Grosse, David K. Duvenaud
• Contextual bandits with surrogate losses: Margin bounds and efficient algorithms Dylan J. Foster, Akshay Krishnamurthy
• Representation Learning for Treatment Effect Estimation from Observational Data Liuyi Yao, Sheng Li, Yaliang Li, Mengdi Huai, Jing Gao, Aidong Zhang
• Representation Balancing MDPs for Off-policy Policy Evaluation Yao Liu, Omer Gottesman, Aniruddh Raghu, Matthieu Komorowski, Aldo A. Faisal, Finale Doshi-Velez, Emma Brunskill
• Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering Medhini Narasimhan, Svetlana Lazebnik, Alexander Schwing
• Causal Discovery from Discrete Data using Hidden Compact Representation Ruichu Cai, Jie Qiao, Kun Zhang, Zhenjie Zhang, Zhifeng Hao
• Natasha 2: Faster Non-Convex Optimization Than SGD Zeyuan Allen-Zhu
• Minimax Statistical Learning with Wasserstein distances Jaeho Lee, Maxim Raginsky
• Provable Variational Inference for Constrained Log-Submodular Models Josip Djolonga, Stefanie Jegelka, Andreas Krause
• Learning Hierarchical Semantic Image Manipulation through Structured Representations Seunghoon Hong, Xinchen Yan, Thomas S. Huang, Honglak Lee
• Processing of missing data by neural networks Marek Śmieja, Łukasz Struski, Jacek Tabor, Bartosz Zieliński, Przemysław Spurek
• Safe Active Learning for Time-Series Modeling with Gaussian Processes Christoph Zimmer, Mona Meister, Duy Nguyen-Tuong
• Optimal Algorithms for Non-Smooth Distributed Optimization in Networks Kevin Scaman, Francis Bach, Sebastien Bubeck, Laurent Massoulié, Yin Tat Lee
• Computing Higher Order Derivatives of Matrix and Tensor Expressions Soeren Laue, Matthias Mitterreiter, Joachim Giesen
• Paraphrasing Complex Network: Network Compression via Factor Transfer Jangho Kim, Seonguk Park, Nojun Kwak
• Analytic solution and stationary phase approximation for the Bayesian lasso and elastic net Tom Michoel
• Demystifying excessively volatile human learning: A Bayesian persistent prior and a neural approximation Chaitanya Ryali, Gautam Reddy, Angela J. Yu
• Empirical Risk Minimization Under Fairness Constraints Michele Donini, Luca Oneto, Shai Ben-David, John S. Shawe-Taylor, Massimiliano Pontil
• Unsupervised Learning of Shape and Pose with Differentiable Point Clouds Eldar Insafutdinov, Alexey Dosovitskiy
• Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces Motoya Ohnishi, Masahiro Yukawa, Mikael Johansson, Masashi Sugiyama
• Gradient Descent Meets Shift-and-Invert Preconditioning for Eigenvector Computation Zhiqiang Xu
• Factored Bandits Julian Zimmert, Yevgeny Seldin
• Delta-encoder: an effective sample synthesis method for few-shot object recognition Eli Schwartz, Leonid Karlinsky, Joseph Shtok, Sivan Harary, Mattias Marder, Abhishek Kumar, Rogerio Feris, Raja Giryes, Alex Bronstein
• Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators Isao Ishikawa, Keisuke Fujii, Masahiro Ikeda, Yuka Hashimoto, Yoshinobu Kawahara
• Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization Jie Cao, Yibo Hu, Hongwen Zhang, Ran He, Zhenan Sun
• Mirrored Langevin Dynamics Ya-Ping Hsieh, Ali Kavis, Paul Rolland, Volkan Cevher
• Moonshine: Distilling with Cheap Convolutions Elliot J. Crowley, Gavin Gray, Amos J. Storkey
• Stochastic Cubic Regularization for Fast Nonconvex Optimization Nilesh Tripuraneni, Mitchell Stern, Chi Jin, Jeffrey Regier, Michael I. Jordan
• Adaptation to Easy Data in Prediction with Limited Advice Tobias Thune, Yevgeny Seldin
• Differentially Private Bayesian Inference for Exponential Families Garrett Bernstein, Daniel R. Sheldon
• Playing hard exploration games by watching YouTube Yusuf Aytar, Tobias Pfaff, David Budden, Thomas Paine, Ziyu Wang, Nando de Freitas
• Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base Daya Guo, Duyu Tang, Nan Duan, Ming Zhou, Jian Yin
• Norm-Ranging LSH for Maximum Inner Product Search Xiao Yan, Jinfeng Li, Xinyan Dai, Hongzhi Chen, James Cheng
• Optimization over Continuous and Multi-dimensional Decisions with Observational Data Dimitris Bertsimas, Christopher McCord
• Fast Estimation of Causal Interactions using Wold Processes Flavio Figueiredo, Guilherme Resende Borges, Pedro O.S. Vaz de Melo, Renato Assunção
• When do random forests fail? Cheng Tang, Damien Garreau, Ulrike von Luxburg
• Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes Ronan Fruit, Matteo Pirotta, Alessandro Lazaric
• Optimistic optimization of a Brownian Jean-Bastien Grill, Michal Valko, Remi Munos
• Practical Methods for Graph Two-Sample Testing Debarghya Ghoshdastidar, Ulrike von Luxburg
• NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations Marco Ciccone, Marco Gallieri, Jonathan Masci, Christian Osendorfer, Faustino Gomez
• On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport Lénaïc Chizat, Francis Bach
• Constructing Deep Neural Networks by Bayesian Network Structure Learning Raanan Y. Rohekar, Shami Nisimov, Yaniv Gurwicz, Guy Koren, Gal Novik
• Weakly Supervised Dense Event Captioning in Videos Xuguang Duan, Wenbing Huang, Chuang Gan, Jingdong Wang, Wenwu Zhu, Junzhou Huang
• Faithful Inversion of Generative Models for Effective Amortized Inference Stefan Webb, Adam Golinski, Rob Zinkov, Siddharth Narayanaswamy, Tom Rainforth, Yee Whye Teh, Frank Wood
• From Stochastic Planning to Marginal MAP Hao Cui, Radu Marinescu, Roni Khardon
• On Binary Classification in Extreme Regions Hamid JALALZAI, Stephan Clémençon, Anne Sabourin
• Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models Yining Wang, Xi Chen, Yuan Zhou
• Q-learning with Nearest Neighbors Devavrat Shah, Qiaomin Xie
• Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization Pan Xu, Jinghui Chen, Difan Zou, Quanquan Gu
• Asymptotic optimality of adaptive importance sampling François Portier, Bernard Delyon
• Learning latent variable structured prediction models with Gaussian perturbations Kevin Bello, Jean Honorio
• The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal Jiantao Jiao, Weihao Gao, Yanjun Han
• Deep Reinforcement Learning of Marked Temporal Point Processes Utkarsh Upadhyay, Abir De, Manuel Gomez Rodriguez
• Evidential Deep Learning to Quantify Classification Uncertainty Murat Sensoy, Lance Kaplan, Melih Kandemir
• Parsimonious Bayesian deep networks Mingyuan Zhou
• Single-Agent Policy Tree Search With Guarantees Laurent Orseau, Levi Lelis, Tor Lattimore, Theophane Weber
• Semi-crowdsourced Clustering with Deep Generative Models Yucen Luo, TIAN TIAN, Jiaxin Shi, Jun Zhu, Bo Zhang
• The committee machine: Computational to statistical gaps in learning a two-layers neural network Benjamin Aubin, Antoine Maillard, jean barbier, Florent Krzakala, Nicolas Macris, Lenka Zdeborová
• Realistic Evaluation of Deep Semi-Supervised Learning Algorithms Avital Oliver, Augustus Odena, Colin A. Raffel, Ekin Dogus Cubuk, Ian Goodfellow
• Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular Reward Lixing Chen, Jie Xu, Zhuo Lu
• Training deep learning based denoisers without ground truth data Shakarim Soltanayev, Se Young Chun
• Re-evaluating evaluation David Balduzzi, Karl Tuyls, Julien Perolat, Thore Graepel
• Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibres Oisín Moran, Piergiorgio Caramazza, Daniele Faccio, Roderick Murray-Smith
• Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals Tom Dupré la Tour, Thomas Moreau, Mainak Jas, Alexandre Gramfort
• Data-Efficient Hierarchical Reinforcement Learning Ofir Nachum, Shixiang (Shane) Gu, Honglak Lee, Sergey Levine
• Speaker-Follower Models for Vision-and-Language Navigation Daniel Fried, Ronghang Hu, Volkan Cirik, Anna Rohrbach, Jacob Andreas, Louis-Philippe Morency, Taylor Berg-Kirkpatrick, Kate Saenko, Dan Klein, Trevor Darrell
• Inequity aversion improves cooperation in intertemporal social dilemmas Edward Hughes, Joel Z. Leibo, Matthew Phillips, Karl Tuyls, Edgar Dueñez-Guzman, Antonio García Castañeda, Iain Dunning, Tina Zhu, Kevin McKee, Raphael Koster, Heather Roff, Thore Graepel
• Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds David Reeb, Andreas Doerr, Sebastian Gerwinn, Barbara Rakitsch
• Probabilistic Matrix Factorization for Automated Machine Learning Nicolo Fusi, Rishit Sheth, Melih Elibol
• Stochastic Spectral and Conjugate Descent Methods Dmitry Kovalev, Peter Richtarik, Eduard Gorbunov, Elnur Gasanov
• Recurrent Relational Networks Rasmus Palm, Ulrich Paquet, Ole Winther
• But How Does It Work in Theory? Linear SVM with Random Features Yitong Sun, Anna Gilbert, Ambuj Tewari
• Learning to Optimize Tensor Programs Tianqi Chen, Lianmin Zheng, Eddie Yan, Ziheng Jiang, Thierry Moreau, Luis Ceze, Carlos Guestrin, Arvind Krishnamurthy
• Boosting Black Box Variational Inference Francesco Locatello, Gideon Dresdner, Rajiv Khanna, Isabel Valera, Gunnar Raetsch
• Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes Hassan Ashtiani, Shai Ben-David, Nicholas Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan
• Actor-Critic Policy Optimization in Partially Observable Multiagent Environments Sriram Srinivasan, Marc Lanctot, Vinicius Zambaldi, Julien Perolat, Karl Tuyls, Remi Munos, Michael Bowling
• Step Size Matters in Deep Learning Kamil Nar, Shankar Sastry
• Derivative Estimation in Random Design Yu Liu, Kris De Brabanter
• Zeroth-order (Non)-Convex Stochastic Optimization via Conditional Gradient and Gradient Updates Krishnakumar Balasubramanian, Saeed Ghadimi
• Latent Gaussian Activity Propagation: Using Smoothness and Structure to Separate and Localize Sounds in Large Noisy EnvironmentsDaniel Johnson, Daniel Gorelik, Ross E. Mawhorter, Kyle Suver, Weiqing Gu, Steven Xing, Cody Gabriel, Peter Sankhagowit
• Hybrid-MST: A Hybrid Active Sampling Strategy for Pairwise Preference Aggregation JING LI, Rafal Mantiuk, Junle Wang, Suiyi Ling, Patrick Le Callet
• Infinite-Horizon Gaussian Processes Arno Solin, James Hensman, Richard E. Turner
• Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization Minshuo Chen, Lin Yang, Mengdi Wang, Tuo Zhao
• Sequence-to-Segment Networks for Segment Detection Zijun Wei, Boyu Wang, Minh Hoai Nguyen, Jianming Zhang, Zhe Lin, Xiaohui Shen, Radomir Mech, Dimitris Samaras
• Scaling the Poisson GLM to massive neural datasets through polynomial approximations David Zoltowski, Jonathan W. Pillow
• Multiplicative Weights Updates with Constant Step-Size in Graphical Constant-Sum Games Yun Kuen Cheung
• Why Is My Classifier Discriminatory? Irene Chen, Fredrik D. Johansson, David Sontag
• Multi-Layered Gradient Boosting Decision Trees Ji Feng, Yang Yu, Zhi-Hua Zhou
• Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning Tom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor
• Communication Efficient Parallel Algorithms for Optimization on Manifolds Bayan Saparbayeva, Michael Zhang, Lizhen Lin
• Neural Code Comprehension: A Learnable Representation of Code Semantics Tal Ben-Nun, Alice Shoshana Jakobovits, Torsten Hoefler
• Tight Bounds for Collaborative PAC Learning via Multiplicative Weights Jiecao Chen, Qin Zhang, Yuan Zhou
• BinGAN: Learning Compact Binary Descriptors with a Regularized GAN Maciej Zieba, Piotr Semberecki, Tarek El-Gaaly, Tomasz Trzcinski
• Modern Neural Networks Generalize on Small Data Sets Matthew Olson, Abraham Wyner, Richard Berk
• Escaping Saddle Points in Constrained Optimization Aryan Mokhtari, Asuman Ozdaglar, Ali Jadbabaie
• Adversarial Attacks on Stochastic Bandits Kwang-Sung Jun, Lihong Li, Yuzhe Ma, Jerry Zhu
• Optimal Subsampling with Influence Functions Daniel Ting, Eric Brochu
• A Bandit Approach to Sequential Experimental Design with False Discovery Control Kevin G. Jamieson, Lalit Jain
• Equality of Opportunity in Classification: A Causal Approach Junzhe Zhang, Elias Bareinboim
• Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization Tianyi Liu, Shiyang Li, Jianping Shi, Enlu Zhou, Tuo Zhao
• Unsupervised Attention-guided Image-to-Image Translation Youssef Alami Mejjati, Christian Richardt, James Tompkin, Darren Cosker, Kwang In Kim
• Inferring Networks From Random Walk-Based Node Similarities Jeremy Hoskins, Cameron Musco, Christopher Musco, Babis Tsourakakis
• NEON2: Finding Local Minima via First-Order Oracles Zeyuan Allen-Zhu, Yuanzhi Li
• Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization Sijia Liu, Bhavya Kailkhura, Pin-Yu Chen, Paishun Ting, Shiyu Chang, Lisa Amini
• Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting Hippolyt Ritter, Aleksandar Botev, David Barber
• DeepProbLog: Neural Probabilistic Logic Programming Robin Manhaeve, Sebastijan Dumancic, Angelika Kimmig, Thomas Demeester, Luc De Raedt
• Convergence of Cubic Regularization for Nonconvex Optimization under KL Property Yi Zhou, Zhe Wang, Yingbin Liang
• Direct Estimation of Differences in Causal Graphs Yuhao Wang, Chandler Squires, Anastasiya Belyaeva, Caroline Uhler
• Sublinear Time Low-Rank Approximation of Distance Matrices Ainesh Bakshi, David Woodruff
• Variational PDEs for Acceleration on Manifolds and Application to Diffeomorphisms Ganesh Sundaramoorthi, Anthony Yezzi
• Bayesian Inference of Temporal Task Specifications from Demonstrations Ankit Shah, Pritish Kamath, Julie A. Shah, Shen Li
• Data center cooling using model-predictive control Nevena Lazic, Craig Boutilier, Tyler Lu, Eehern Wong, Binz Roy, MK Ryu, Greg Imwalle
• Acceleration through Optimistic No-Regret Dynamics Jun-Kun Wang, Jacob D. Abernethy
• Lipschitz regularity of deep neural networks: analysis and efficient estimation Aladin Virmaux, Kevin Scaman
• Minimax Estimation of Neural Net Distance Kaiyi Ji, Yingbin Liang
• Leveraging the Exact Likelihood of Deep Latent Variable Models Pierre-Alexandre Mattei, Jes Frellsen
• Bipartite Stochastic Block Models with Tiny Clusters Stefan Neumann
• Learning sparse neural networks via sensitivity-driven regularization Enzo Tartaglione, Skjalg Lepsøy, Attilio Fiandrotti, Gianluca Francini
• Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization Xiaoxuan Zhang, Mingrui Liu, Xun Zhou, Tianbao Yang
• Direct Runge-Kutta Discretization Achieves Acceleration Jingzhao Zhang, Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie
• Adversarial Examples that Fool both Computer Vision and Time-Limited Humans Gamaleldin Elsayed, Shreya Shankar, Brian Cheung, Nicolas Papernot, Alexey Kurakin, Ian Goodfellow, Jascha Sohl-Dickstein
• Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization Dongruo Zhou, Pan Xu, Quanquan Gu
• Faster Neural Networks Straight from JPEG Lionel Gueguen, Alex Sergeev, Ben Kadlec, Rosanne Liu, Jason Yosinski
• TopRank: A practical algorithm for online stochastic ranking Tor Lattimore, Branislav Kveton, Shuai Li, Csaba Szepesvari
• Learning from discriminative feature feedback Sanjoy Dasgupta, Akansha Dey, Nicholas Roberts, Sivan Sabato
• RetGK: Graph Kernels based on Return Probabilities of Random Walks Zhen Zhang, Mianzhi Wang, Yijian Xiang, Yan Huang, Arye Nehorai
• Deep Generative Markov State Models Hao Wu, Andreas Mardt, Luca Pasquali, Frank Noe
• Early Stopping for Nonparametric Testing Meimei Liu, Guang Cheng
• Solving Non-smooth Constrained Programs with Lower Complexity than \mathcal{O}(1/\varepsilon): A Primal-Dual Homotopy Smoothing Approach Xiaohan Wei, Hao Yu, Qing Ling, Michael Neely
• Heterogeneous Bitwidth Binarization in Convolutional Neural Networks Joshua Fromm, Shwetak Patel, Matthai Philipose
• Unsupervised Learning of Object Landmarks through Conditional Image Generation Tomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi
• Probabilistic Neural Programmed Networks for Scene Generation Zhiwei Deng, Jiacheng Chen, YIFANG FU, Greg Mori
• The streaming rollout of deep networks - towards fully model-parallel execution Volker Fischer, Jan Koehler, Thomas Pfeil
• KONG: Kernels for ordered-neighborhood graphs Moez Draief, Konstantin Kutzkov, Kevin Scaman, Milan Vojnovic
• GumBolt: Extending Gumbel trick to Boltzmann priors Amir H. Khoshaman, Mohammad Amin
• Neural Networks Trained to Solve Differential Equations Learn General Representations Martin Magill, Faisal Qureshi, Hendrick de Haan
• Beauty-in-averageness and its contextual modulations: A Bayesian statistical account Chaitanya Ryali, Angela J. Yu
• Distributed Weight Consolidation: A Brain Segmentation Case Study Patrick McClure, Charles Y. Zheng, Jakub Kaczmarzyk, John Rogers-Lee, Satra Ghosh, Dylan Nielson, Peter A. Bandettini, Francisco Pereira
• Efficient Projection onto the Perfect Phylogeny Model Bei Jia, Surjyendu Ray, Sam Safavi, José Bento
• TETRIS: TilE-matching the TRemendous Irregular Sparsity Yu Ji, Ling Liang, Lei Deng, Youyang Zhang, Youhui Zhang, Yuan Xie
• Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification Harsh Shrivastava, Eugene Bart, Bob Price, Hanjun Dai, Bo Dai, Srinivas Aluru
• Differentially Private Robust Low-Rank Approximation Raman Arora, Vladimir braverman, Jalaj Upadhyay
• Meta-Learning MCMC Proposals Tongzhou Wang, YI WU, Dave Moore, Stuart J. Russell
• An Information-Theoretic Analysis for Thompson Sampling with Many Actions Shi Dong, Benjamin Van Roy
• Flexible and accurate inference and learning for deep generative models Eszter Vértes, Maneesh Sahani
• The Price of Privacy for Low-rank Factorization Jalaj Upadhyay
• Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu
• Bilevel Distance Metric Learning for Robust Image Recognition Jie Xu, Lei Luo, Cheng Deng, Heng Huang
• Differentially Private Uniformly Most Powerful Tests for Binomial Data Jordan Awan, Aleksandra Slavković
• Scalable Coordinated Exploration in Concurrent Reinforcement Learning Maria Dimakopoulou, Ian Osband, Benjamin Van Roy
• Integrated accounts of behavioral and neuroimaging data using flexible recurrent neural network models Amir Dezfouli, Richard Morris, Fabio T. Ramos, Peter Dayan, Bernard Balleine
• BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML Training Songtao Wang, Dan Li, Yang Cheng, Jinkun Geng, Yanshu Wang, Shuai Wang, Shu-Tao Xia, Jianping Wu
• Inexact trust-region algorithms on Riemannian manifolds Hiroyuki Kasai, Bamdev Mishra
• Can We Gain More from Orthogonality Regularizations in Training Deep Networks? Nitin Bansal, Xiaohan Chen, Zhangyang Wang
• Binary Rating Estimation with Graph Side Information Kwangjun Ahn, Kangwook Lee, Hyunseung Cha, Changho Suh
• SimplE Embedding for Link Prediction in Knowledge Graphs Seyed Mehran Kazemi, David Poole
• Differentially Private Contextual Linear Bandits Roshan Shariff, Or Sheffet
• Submodular Field Grammars: Representation, Inference, and Application to Image Parsing Abram L. Friesen, Pedro M. Domingos
• A Bridging Framework for Model Optimization and Deep Propagation Risheng Liu, Shichao Cheng, xiaokun liu, Long Ma, Xin Fan, Zhongxuan Luo
• Completing State Representations using Spectral Learning Nan Jiang, Alex Kulesza, Satinder Singh
• Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates Yining Wang, Sivaraman Balakrishnan, Aarti Singh
• Adding One Neuron Can Eliminate All Bad Local Minima SHIYU LIANG, Ruoyu Sun, Jason D. Lee, R. Srikant
• Mean-field theory of graph neural networks in graph partitioning Tatsuro Kawamoto, Masashi Tsubaki, Tomoyuki Obuchi
• The Physical Systems Behind Optimization Algorithms Lin Yang, Raman Arora, Vladimir braverman, Tuo Zhao
• Mallows Models for Top-k Lists Flavio Chierichetti, Anirban Dasgupta, Shahrzad Haddadan, Ravi Kumar, Silvio Lattanzi
• Amortized Inference Regularization Rui Shu, Hung H. Bui, Shengjia Zhao, Mykel J. Kochenderfer, Stefano Ermon
• Maximum Causal Tsallis Entropy Imitation Learning Kyungjae Lee, Sungjoon Choi, Songhwai Oh
• Limited Memory Kelley's Method Converges for Composite Convex and Submodular Objectives Song Zhou, Swati Gupta, Madeleine Udell
• Semi-Supervised Learning with Declaratively Specified Entropy Constraints Haitian Sun, William W. Cohen, Lidong Bing
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems Linfeng Zhang, Jiequn Han, Han Wang, Wissam Saidi, Roberto Car, Weinan E
• Sparsified SGD with Memory Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi
• Exponentiated Strongly Rayleigh Distributions Zelda E. Mariet, Suvrit Sra, Stefanie Jegelka
• Importance Weighting and Variational Inference Justin Domke, Daniel R. Sheldon
• Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis Ye Jia, Yu Zhang, Ron Weiss, Quan Wang, Jonathan Shen, Fei Ren, zhifeng Chen, Patrick Nguyen, Ruoming Pang, Ignacio Lopez Moreno, Yonghui Wu
• Expanding Holographic Embeddings for Knowledge Completion Yexiang Xue, Yang Yuan, Zhitian Xu, Ashish Sabharwal
• Lifelong Inverse Reinforcement Learning Jorge Armando Mendez Mendez, Shashank Shivkumar, Eric Eaton
• Explaining Deep Learning Models -- A Bayesian Non-parametric Approach Wenbo Guo, Sui Huang, Yunzhe Tao, Xinyu Xing, Lin Lin
• Third-order Smoothness Helps: Faster Stochastic Optimization Algorithms for Finding Local Minima Yaodong Yu, Pan Xu, Quanquan Gu
• COLA: Decentralized Linear Learning Lie He, An Bian, Martin Jaggi
• MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare Edward Choi, Cao Xiao, Walter Stewart, Jimeng Sun
• Adaptive Sampling Towards Fast Graph Representation Learning Wenbing Huang, Tong Zhang, Yu Rong, Junzhou Huang
• Hunting for Discriminatory Proxies in Linear Regression Models Samuel Yeom, Anupam Datta, Matt Fredrikson
• Towards Robust Detection of Adversarial Examples Tianyu Pang, Chao Du, Yinpeng Dong, Jun Zhu
• Active Matting Xin Yang, Ke Xu, Shaozhe Chen, Shengfeng He, Baocai Yin Yin, Rynson Lau
• Learning filter widths of spectral decompositions with wavelets Haidar Khan, Bulent Yener
• Byzantine Stochastic Gradient Descent Dan Alistarh, Zeyuan Allen-Zhu, Jerry Li
• PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits Bianca Dumitrascu, Karen Feng, Barbara Engelhardt
• Spectral Filtering for General Linear Dynamical Systems Elad Hazan, HOLDEN LEE, Karan Singh, Cyril Zhang, Yi Zhang
• On Learning Intrinsic Rewards for Policy Gradient Methods Zeyu Zheng, Junhyuk Oh, Satinder Singh
• Boolean Decision Rules via Column Generation Sanjeeb Dash, Oktay Gunluk, Dennis Wei
• Adversarial Text Generation via Feature-Mover's Distance Liqun Chen, Shuyang Dai, Chenyang Tao, Haichao Zhang, Zhe Gan, Dinghan Shen, Yizhe Zhang, Guoyin Wang, Ruiyi Zhang, Lawrence Carin
• Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions Mingrui Liu, Xiaoxuan Zhang, Lijun Zhang, Jing Rong, Tianbao Yang
• Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels Shahin Shahrampour, Vahid Tarokh
• A Mathematical Model For Optimal Decisions In A Representative Democracy Malik Magdon-Ismail, Lirong Xia
• Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making Nishant Desai, Andrew Critch, Stuart J. Russell
• Non-metric Similarity Graphs for Maximum Inner Product Search Stanislav Morozov, Artem Babenko
• Recurrently Controlled Recurrent Networks Yi Tay, Anh Tuan Luu, Siu Cheung Hui
• Fast greedy algorithms for dictionary selection with generalized sparsity constraints Kaito Fujii, Tasuku Soma
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models Kurtland Chua, Roberto Calandra, Rowan McAllister, Sergey Levine
• A Smoother Way to Train Structured Prediction Models Venkata Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaid Harchaoui
• Context-dependent upper-confidence bounds for directed exploration Raksha Kumaraswamy, Matthew Schlegel, Adam White, Martha White
• A Unified View of Piecewise Linear Neural Network Verification Rudy R. Bunel, Ilker Turkaslan, Philip Torr, Pushmeet Kohli, Pawan K. Mudigonda
• Hierarchical Graph Representation Learning with Differentiable Pooling Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, Jure Leskovec
• Non-Ergodic Alternating Proximal Augmented Lagrangian Algorithms with Optimal Rates Quoc Tran Dinh
• Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces Boyla Mainsah, Dmitry Kalika, Leslie Collins, Siyuan Liu, Chandra Throckmorton
• Porcupine Neural Networks: Approximating Neural Network Landscapes Soheil Feizi, Hamid Javadi, Jesse Zhang, David Tse
• Fairness Through Computationally-Bounded Awareness Michael Kim, Omer Reingold, Guy Rothblum
• Adaptive Negative Curvature Descent with Applications in Non-convex Optimization Mingrui Liu, Zhe Li, Xiaoyu Wang, Jinfeng Yi, Tianbao Yang
• Is Q-Learning Provably Efficient? Chi Jin, Zeyuan Allen-Zhu, Sebastien Bubeck, Michael I. Jordan
• Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections Xin Zhang, Armando Solar-Lezama, Rishabh Singh
• Measures of distortion for machine learning Leena Chennuru Vankadara, Ulrike von Luxburg
• On the Local Minima of the Empirical Risk Chi Jin, Lydia T. Liu, Rong Ge, Michael I. Jordan
• Densely Connected Attention Propagation for Reading Comprehension Yi Tay, Anh Tuan Luu, Siu Cheung Hui, Jian Su
• Bandit Learning with Positive Externalities Virag Shah, Jose Blanchet, Ramesh Johari
• Learning Confidence Sets using Support Vector Machines Wenbo Wang, Xingye Qiao
• Efficient Neural Network Robustness Certification with General Activation Functions Huan Zhang, Tsui-Wei Weng, Pin-Yu Chen, Cho-Jui Hsieh, Luca Daniel
• Hessian-based Analysis of Large Batch Training and Robustness to Adversaries Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney
• Neural Edit Operations for Biological Sequences Satoshi Koide, Keisuke Kawano, Takuro Kutsuna
• Objective and efficient inference for couplings in neuronal networks Yu Terada, Tomoyuki Obuchi, Takuya Isomura, Yoshiyuki Kabashima
• Learning from Group Comparisons: Exploiting Higher Order Interactions Yao Li, Minhao Cheng, Kevin Fujii, Fushing Hsieh, Cho-Jui Hsieh
• Supervising Unsupervised Learning Vikas Garg
• Nonparametric Bayesian Lomax delegate racing for survival analysis with competing risks Quan Zhang, Mingyuan Zhou
• Adversarially Robust Generalization Requires More Data Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Madry
• Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents Edoardo Conti, Vashisht Madhavan, Felipe Petroski Such, Joel Lehman, Kenneth Stanley, Jeff Clune
• Practical exact algorithm for trembling-hand equilibrium refinements in games Gabriele Farina, Nicola Gatti, Tuomas Sandholm
• LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning Tianyi Chen, Georgios Giannakis, Tao Sun, Wotao Yin
• Scalable Robust Matrix Factorization with Nonconvex Loss Quanming Yao, James Kwok
• Power-law efficient neural codes provide general link between perceptual bias and discriminability Michael Morais, Jonathan W. Pillow
• Geometry-Aware Recurrent Neural Networks for Active Visual Recognition Ricson Cheng, Ziyan Wang, Katerina Fragkiadaki
• Unsupervised Adversarial Invariance Ayush Jaiswal, Rex Yue Wu, Wael Abd-Almageed, Prem Natarajan
• Content preserving text generation with attribute controls Lajanugen Logeswaran, Honglak Lee, Samy Bengio
• Multi-armed Bandits with Compensation Siwei Wang, Longbo Huang
• GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training Mingchao Yu, Zhifeng Lin, Krishna Narra, Songze Li, Youjie Li, Nam Sung Kim, Alexander Schwing, Murali Annavaram, Salman Avestimehr
• Learning in Games with Lossy Feedback Zhengyuan Zhou, Panayotis Mertikopoulos, Susan Athey, Nicholas Bambos, Peter W. Glynn, Yinyu Ye
• Scalable methods for 8-bit training of neural networks Ron Banner, Itay Hubara, Elad Hoffer, Daniel Soudry
• Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization Zhihui Zhu, Xiao Li, Kai Liu, Qiuwei Li
• Link Prediction Based on Graph Neural Networks Muhan Zhang, Yixin Chen
• Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit task Dalin Guo, Angela J. Yu
• Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model Aaron Sidford, Mengdi Wang, Xian Wu, Lin Yang, Yinyu Ye
• ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions Hongyang Gao, Zhengyang Wang, Shuiwang Ji
• Causal Inference and Mechanism Clustering of A Mixture of Additive Noise Models Shoubo Hu, Zhitang Chen, Vahid Partovi Nia, Laiwan CHAN, Yanhui Geng
• Contour location via entropy reduction leveraging multiple information sources Alexandre Marques, Remi Lam, Karen Willcox
• Assessing Generative Models via Precision and Recall Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet, Sylvain Gelly
• Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
• A Convex Duality Framework for GANs Farzan Farnia, David Tse
• Horizon-Independent Minimax Linear Regression Alan Malek, Peter L. Bartlett
• Exploiting Numerical Sparsity for Efficient Learning : Faster Eigenvector Computation and Regression Neha Gupta, Aaron Sidford
• Experimental Design for Cost-Aware Learning of Causal Graphs Erik Lindgren, Murat Kocaoglu, Alexandros G. Dimakis, Sriram Vishwanath
• Task-Driven Convolutional Recurrent Models of the Visual System Aran Nayebi, Daniel Bear, Jonas Kubilius, Kohitij Kar, Surya Ganguli, David Sussillo, James J. DiCarlo, Daniel L. Yamins
• Meta-Reinforcement Learning of Structured Exploration Strategies Abhishek Gupta, Russell Mendonca, YuXuan Liu, Pieter Abbeel, Sergey Levine
• Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation Tomoya Murata, Taiji Suzuki
• Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance Neal Jean, Sang Michael Xie, Stefano Ermon
• Generalizing to Unseen Domains via Adversarial Data Augmentation Riccardo Volpi, Hongseok Namkoong, Ozan Sener, John C. Duchi, Vittorio Murino, Silvio Savarese
• Hyperbolic Neural Networks Octavian Ganea, Gary Becigneul, Thomas Hofmann
• Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation Qiang Liu, Lihong Li, Ziyang Tang, Dengyong Zhou
• Learning Task Specifications from Demonstrations Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho, Sanjit Seshia
• Learning a latent manifold of odor representations from neural responses in piriform cortex Anqi Wu, Stan Pashkovski, Sandeep R. Datta, Jonathan W. Pillow
• Fully Understanding The Hashing Trick Casper B. Freksen, Lior Kamma, Kasper Green Larsen
• Evolved Policy Gradients Rein Houthooft, Yuhua Chen, Phillip Isola, Bradly Stadie, Filip Wolski, OpenAI Jonathan Ho, Pieter Abbeel
• The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network Jeffrey Pennington, Pratik Worah
• Learning Concave Conditional Likelihood Models for Improved Analysis of Tandem Mass Spectra John T. Halloran, David M. Rocke
• Differentially Private k-Means with Constant Multiplicative Error Uri Stemmer, Haim Kaplan
• Policy Optimization via Importance Sampling Alberto Maria Metelli, Matteo Papini, Francesco Faccio, Marcello Restelli
• Estimating Learnability in the Sublinear Data Regime Weihao Kong, Gregory Valiant
• Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation Shivapratap Gopakumar, Sunil Gupta, Santu Rana, Vu Nguyen, Svetha Venkatesh
• Community Exploration: From Offline Optimization to Online Learning Xiaowei Chen, Weiran Huang, Wei Chen, John C. S. Lui
• A Dual Framework for Low-rank Tensor Completion Madhav Nimishakavi, Pratik Kumar Jawanpuria, Bamdev Mishra
• Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames Geneviève Robin, Hoi-To Wai, Julie Josse, Olga Klopp, Eric Moulines
• Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing Zehong Hu, Yitao Liang, Jie Zhang, Zhao Li, Yang Liu
• Middle-Out Decoding Shikib Mehri, Leonid Sigal
• First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time Yi Xu, Jing Rong, Tianbao Yang
• To Trust Or Not To Trust A Classifier Heinrich Jiang, Been Kim, Melody Guan, Maya Gupta
• Reparameterization Gradient for Non-differentiable Models Wonyeol Lee, Hangyeol Yu, Hongseok Yang
• A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization Zhize Li, Jian Li
• Multimodal Generative Models for Scalable Weakly-Supervised Learning Mike Wu, Noah Goodman
• How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery? Richard Zhang, Cedric Josz, Somayeh Sojoudi, Javad Lavaei
• Occam's razor is insufficient to infer the preferences of irrational agents Stuart Armstrong, Sören Mindermann
• Manifold Structured Prediction Alessandro Rudi, Carlo Ciliberto, GianMaria Marconi, Lorenzo Rosasco
• Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity Laming Chen, Guoxin Zhang, Eric Zhou
• Learning Others' Intentional Models in Multi-Agent Settings Using Interactive POMDPs Yanlin Han, Piotr Gmytrasiewicz
• Contextual Pricing for Lipschitz Buyers Jieming Mao, Renato Leme, Jon Schneider
• Online Improper Learning with an Approximation Oracle Elad Hazan, Wei Hu, Yuanzhi Li, zhiyuan li
• Bandit Learning in Concave N-Person Games Mario Bravo, David Leslie, Panayotis Mertikopoulos
• On Fast Leverage Score Sampling and Optimal Learning Alessandro Rudi, Daniele Calandriello, Luigi Carratino, Lorenzo Rosasco
• Unsupervised Video Object Segmentation for Deep Reinforcement Learning Vikash Goel, Jameson Weng, Pascal Poupart
• Efficient inference for time-varying behavior during learning Nicholas A. Roy, Ji Hyun Bak, Athena Akrami, Carlos Brody, Jonathan W. Pillow
• Learning convex polytopes with margin Lee-Ad Gottlieb, Eran Kaufman, Aryeh Kontorovich, Gabriel Nivasch
• Critical initialisation for deep signal propagation in noisy rectifier neural networks Arnu Pretorius, Elan van Biljon, Steve Kroon, Herman Kamper
• Insights on representational similarity in neural networks with canonical correlation Ari Morcos, Maithra Raghu, Samy Bengio
• Variational Inference with Tail-adaptive f-Divergence Dilin Wang, Hao Liu, Qiang Liu
• Mental Sampling in Multimodal Representations Jianqiao Zhu, Adam Sanborn, Nick Chater
• Adversarially Robust Optimization with Gaussian Processes Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, Volkan Cevher
• Learning to Multitask Yu Zhang, Ying Wei, Qiang Yang
• Loss Functions for Multiset Prediction Sean Welleck, Zixin Yao, Yu Gai, Jialin Mao, Zheng Zhang, Kyunghyun Cho
• Computing Kantorovich-Wasserstein Distances on d-dimensional histograms using (d+1)-partite graphs Gennaro Auricchio, Federico Bassetti, Stefano Gualandi, Marco Veneroni
• Neural Interaction Transparency (NIT): Disentangling Learned Interactions for Improved Interpretability Michael Tsang, Hanpeng Liu, Sanjay Purushotham, Pavankumar Murali, Yan Liu
• CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces Liheng Zhang, Marzieh Edraki, Guo-Jun Qi
• Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence Trong Dinh Thac Do, Longbing Cao
• Masking: A New Perspective of Noisy Supervision Bo Han, Jiangchao Yao, Gang Niu, Mingyuan Zhou, Ivor Tsang, Ya Zhang, Masashi Sugiyama
• On GANs and GMMs Eitan Richardson, Yair Weiss
• Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance Giulia Luise, Alessandro Rudi, Massimiliano Pontil, Carlo Ciliberto
• Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching Stepan Tulyakov, Anton Ivanov, François Fleuret
• A Bayes-Sard Cubature Method Toni Karvonen, Chris J. Oates, Simo Sarkka
• Dual Swap Disentangling Zunlei Feng, Xinchao Wang, Chenglong Ke, An-Xiang Zeng, Dacheng Tao, Mingli Song
• Diverse Ensemble Evolution: Curriculum Data-Model Marriage Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes
• Binary Classification from Positive-Confidence Data Takashi Ishida, Gang Niu, Masashi Sugiyama
• Deep Generative Models for Distribution-Preserving Lossy Compression Michael Tschannen, Eirikur Agustsson, Mario Lucic
• Exact natural gradient in deep linear networks and its application to the nonlinear case Alberto Bernacchia, Mate Lengyel, Guillaume Hennequin
• Constructing Fast Network through Deconstruction of Convolution Yunho Jeon, Junmo Kim
• Memory Replay GANs: Learning to Generate New Categories without Forgetting Chenshen Wu, Luis Herranz, Xialei Liu, yaxing wang, Joost van de Weijer, Bogdan Raducanu
• The Convergence of Sparsified Gradient Methods Dan Alistarh, Torsten Hoefler, Mikael Johansson, Nikola Konstantinov, Sarit Khirirat, Cedric Renggli
• Automating Bayesian optimization with Bayesian optimization Gustavo Malkomes, Roman Garnett
• Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning yunlong yu, Zhong Ji, Yanwei Fu, Jichang Guo, Yanwei Pang, Zhongfei (Mark) Zhang
• Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification Dimitrios Milios, Raffaello Camoriano, Pietro Michiardi, Lorenzo Rosasco, Maurizio Filippone
• Multi-Task Zipping via Layer-wise Neuron Sharing Xiaoxi He, Zimu Zhou, Lothar Thiele
• Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo Oren Mangoubi, Nisheeth Vishnoi
• Approximation algorithms for stochastic clustering David Harris, Shi Li, Aravind Srinivasan, Khoa Trinh, Thomas Pensyl
• Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks Xiaodong Cui, Wei Zhang, Zoltán Tüske, Michael Picheny
• Learning to Infer Graphics Programs from Hand-Drawn Images Kevin Ellis, Daniel Ritchie, Armando Solar-Lezama, Josh Tenenbaum
• Graphical Generative Adversarial Networks Chongxuan LI, Max Welling, Jun Zhu, Bo Zhang
• Variational Learning on Aggregate Outputs with Gaussian Processes Ho Chung Law, Dino Sejdinovic, Ewan Cameron, Tim Lucas, Seth Flaxman, Katherine Battle, Kenji Fukumizu
• MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models Boyuan Pan, Yazheng Yang, Hao Li, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He
• Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks Ali Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras, Tom Goldstein
• Information Constraints on Auto-Encoding Variational Bayes Romain Lopez, Jeffrey Regier, Michael I. Jordan, Nir Yosef
• Recurrent Transformer Networks for Semantic Correspondence Seungryong Kim, Stephen Lin, SANG RYUL JEON, Dongbo Min, Kwanghoon Sohn
• Online convex optimization for cumulative constraints Jianjun Yuan, Andrew Lamperski
• Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer David Madras, Toni Pitassi, Richard Zemel
• Deep State Space Models for Unconditional Word Generation Florian Schmidt, Thomas Hofmann
• ResNet with one-neuron hidden layers is a Universal Approximator Hongzhou Lin, Stefanie Jegelka
• Transfer of Value Functions via Variational Methods Andrea Tirinzoni, Rafael Rodriguez Sanchez, Marcello Restelli
• The Cluster Description Problem - Complexity Results, Formulations and Approximations Ian Davidson, Antoine Gourru, S Ravi
• Sharp Bounds for Generalized Uniformity Testing Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart
• Deep Neural Networks with Box Convolutions Egor Burkov, Victor Lempitsky
• Learning towards Minimum Hyperspherical Energy Weiyang Liu, Rongmei Lin, Zhen Liu, Lixin Liu, Zhiding Yu, Bo Dai, Le Song
• LF-Net: Learning Local Features from Images Yuki Ono, Eduard Trulls, Pascal Fua, Kwang Moo Yi
• SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, Mohammad Emtiyaz Khan
• Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming Bart van Merrienboer, Dan Moldovan, Alexander Wiltschko
• Multi-domain Causal Structure Learning in Linear Systems AmirEmad Ghassami, Negar Kiyavash, Biwei Huang, Kun Zhang
• Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences Borja Balle, Gilles Barthe, Marco Gaboardi
• Exponentially Weighted Imitation Learning for Batched Historical Data Qing Wang, Jiechao Xiong, Lei Han, peng sun, Han Liu, Tong Zhang
• Algebraic tests of general Gaussian latent tree models Dennis Leung, Mathias Drton
• Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models Minjia Zhang, Wenhan Wang, Xiaodong Liu, Jianfeng Gao, Yuxiong He
• Deep Structured Prediction with Nonlinear Output Transformations Colin Graber, Ofer Meshi, Alexander Schwing
• Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling Emilie Kaufmann, Wouter M. Koolen, Aurélien Garivier
• Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization Bargav Jayaraman, Lingxiao Wang, David Evans, Quanquan Gu
• A no-regret generalization of hierarchical softmax to extreme multi-label classification Marek Wydmuch, Kalina Jasinska, Mikhail Kuznetsov, Róbert Busa-Fekete, Krzysztof Dembczynski
• Efficient Formal Safety Analysis of Neural Networks Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana
• Bayesian Distributed Stochastic Gradient Descent Michael Teng, Frank Wood
• Visualizing the Loss Landscape of Neural Nets Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein
• The Limits of Post-Selection Generalization Jonathan Ullman, Adam Smith, Kobbi Nissim, Uri Stemmer, Thomas Steinke
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation Jiaxuan You, Bowen Liu, Zhitao Ying, Vijay Pande, Jure Leskovec
• On Controllable Sparse Alternatives to Softmax Anirban Laha, Saneem Ahmed Chemmengath, Priyanka Agrawal, Mitesh Khapra, Karthik Sankaranarayanan, Harish G. Ramaswamy
• L4: Practical loss-based stepsize adaptation for deep learning Michal Rolinek, Georg Martius
• Learning Latent Subspaces in Variational Autoencoders Jack Klys, Jake Snell, Richard Zemel
• Turbo Learning for CaptionBot and DrawingBot Qiuyuan Huang, Pengchuan Zhang, Dapeng Wu, Lei Zhang
• Learning to Teach with Dynamic Loss Functions Lijun Wu, Fei Tian, Yingce Xia, Yang Fan, Tao Qin, Lai Jian-Huang, Tie-Yan Liu
• Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation Edward Smith, Scott Fujimoto, David Meger
• Size-Noise Tradeoffs in Generative Networks Bolton Bailey, Matus J. Telgarsky
• Online Adaptive Methods, Universality and Acceleration Yehuda Kfir Levy, Alp Yurtsever, Volkan Cevher
• Compact Generalized Non-local Network Kaiyu Yue, Ming Sun, Yuchen Yuan, Feng Zhou, Errui Ding, Fuxin Xu
• On the Local Hessian in Back-propagation Huishuai Zhang, Wei Chen, Tie-Yan Liu
• The Everlasting Database: Statistical Validity at a Fair Price Blake E. Woodworth, Vitaly Feldman, Saharon Rosset, Nati Srebro
• Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama
• Proximal SCOPE for Distributed Sparse Learning Shenyi Zhao, Gong-Duo Zhang, Ming-Wei Li, Wu-Jun Li
• On Coresets for Logistic Regression Alexander Munteanu, Chris Schwiegelshohn, Christian Sohler, David Woodruff
• Neural Ordinary Differential Equations Tian Qi Chen, Yulia Rubanova, Jesse Bettencourt, David K. Duvenaud
• Unsupervised Learning of Artistic Styles with Archetypal Style Analysis Daan Wynen, Cordelia Schmid, Julien Mairal
• Approximating Real-Time Recurrent Learning with Random Kronecker Factors Asier Mujika, Florian Meier, Angelika Steger
• Contamination Attacks and Mitigation in Multi-Party Machine Learning Jamie Hayes, Olga Ohrimenko
• An Improved Analysis of Alternating Minimization for Structured Multi-Response Regression Sheng Chen, Arindam Banerjee
• Incorporating Context into Language Encoding Models for fMRI Shailee Jain, Alexander Huth
• CatBoost: unbiased boosting with categorical features Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, Andrey Gulin
• Query K-means Clustering and the Double Dixie Cup Problem I Chien, Chao Pan, Olgica Milenkovic
• Training Neural Networks Using Features Replay Zhouyuan Huo, Bin Gu, Heng Huang
• Modeling Dynamic Missingness of Implicit Feedback for Recommendation Menghan Wang, Mingming Gong, Xiaolin Zheng, Kun Zhang
• Representation Learning of Compositional Data Marta Avalos, Richard Nock, Cheng Soon Ong, Julien Rouar, Ke Sun
• Model-based targeted dimensionality reduction for neuronal population data Mikio Aoi, Jonathan W. Pillow
• On gradient regularizers for MMD GANs Michael Arbel, Dougal Sutherland, Mikołaj Bińkowski, Arthur Gretton
• Heterogeneous Multi-output Gaussian Process Prediction Pablo Moreno-Muñoz, Antonio Artés, Mauricio Álvarez
• Large-Scale Stochastic Sampling from the Probability Simplex Jack Baker, Paul Fearnhead, Emily Fox, Christopher Nemeth
• Policy Regret in Repeated Games Raman Arora, Michael Dinitz, Teodor Vanislavov Marinov, Mehryar Mohri
• A Theory-Based Evaluation of Nearest Neighbor Models Put Into Practice Hendrik Fichtenberger, Dennis Rohde
• Banach Wasserstein GAN Jonas Adler, Sebastian Lunz
• Provable Gaussian Embedding with One Observation Ming Yu, Zhuoran Yang, Tuo Zhao, Mladen Kolar, Princeton Zhaoran Wang
• BRITS: Bidirectional Recurrent Imputation for Time Series Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, Yitan Li
• M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search Yelong Shen, Jianshu Chen, Po-Sen Huang, Yuqing Guo, Jianfeng Gao
• Extracting Relationships by Multi-Domain Matching Yitong Li, michael Murias, geraldine Dawson, David E. Carlson
• Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Dmitry Storcheus, Scott Yang
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders Stanislav Pidhorskyi, Ranya Almohsen, Gianfranco Doretto
• Diminishing Returns Shape Constraints for Interpretability and Regularization Maya Gupta, Dara Bahri, Andrew Cotter, Kevin Canini
• Scalable Hyperparameter Transfer Learning Valerio Perrone, Rodolphe Jenatton, Matthias W. Seeger, Cedric Archambeau
• Stochastic Nonparametric Event-Tensor Decomposition Shandian Zhe, Yishuai Du
• Scaling Gaussian Process Regression with Derivatives David Eriksson, Kun Dong, Eric Lee, David Bindel, Andrew G. Wilson
• Differentially Private Testing of Identity and Closeness of Discrete Distributions Jayadev Acharya, Ziteng Sun, Huanyu Zhang
• Bayesian Adversarial Learning Nanyang Ye, Zhanxing Zhu
• Efficient Convex Completion of Coupled Tensors using Coupled Nuclear Norms Kishan Wimalawarne, Hiroshi Mamitsuka
• Maximizing Induced Cardinality Under a Determinantal Point Process Jennifer A. Gillenwater, Alex Kulesza, Sergei Vassilvitskii, Zelda E. Mariet
• Causal Inference with Noisy and Missing Covariates via Matrix Factorization Nathan Kallus, Xiaojie Mao, Madeleine Udell
• rho-POMDPs have Lipschitz-Continuous epsilon-Optimal Value Functions Mathieu Fehr, Olivier Buffet, Vincent Thomas, Jilles Dibangoye
• Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks Agastya Kalra, Abdullah Rashwan, Wei-Shou Hsu, Pascal Poupart, Prashant Doshi, Georgios Trimponias
• Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss Stephen Mussmann, Percy S. Liang
• A Probabilistic U-Net for Segmentation of Ambiguous Images Simon Kohl, Bernardino Romera-Paredes, Clemens Meyer, Jeffrey De Fauw, Joseph R. Ledsam, Klaus Maier-Hein, S. M. Ali Eslami, Danilo Jimenez Rezende, Olaf Ronneberger
• Unorganized Malicious Attacks Detection Ming Pang, Wei Gao, Min Tao, Zhi-Hua Zhou
• Causal Inference via Kernel Deviance Measures Jovana Mitrovic, Dino Sejdinovic, Yee Whye Teh
• Bayesian Alignments of Warped Multi-Output Gaussian Processes Markus Kaiser, Clemens Otte, Thomas Runkler, Carl Henrik Ek
• Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks Yingyezhe Jin, Wenrui Zhang, Peng Li
• Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan
• Efficient online algorithms for fast-rate regret bounds under sparsity Pierre Gaillard, Olivier Wintenberger
• GILBO: One Metric to Measure Them All Alexander A. Alemi, Ian Fischer
• Predictive Uncertainty Estimation via Prior Networks Andrey Malinin, Mark Gales
• Dual Policy Iteration Wen Sun, Geoffrey J. Gordon, Byron Boots, J. Bagnell
• A probabilistic population code based on neural samples Sabyasachi Shivkumar, Richard Lange, Ankani Chattoraj, Ralf Haefner
• Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks Anirvan Sengupta, Cengiz Pehlevan, Mariano Tepper, Alexander Genkin, Dmitri Chklovskii
• On the Convergence and Robustness of Training GANs with Regularized Optimal Transport Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee
• Model-Agnostic Private Learning Raef Bassily, Abhradeep Guha Thakurta, Om Dipakbhai Thakkar
• Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders Tengfei Ma, Jie Chen, Cao Xiao
• Provably Correct Automatic Sub-Differentiation for Qualified Programs Sham M. Kakade, Jason D. Lee
• Deep Homogeneous Mixture Models: Representation, Separation, and Approximation Priyank Jaini, Pascal Poupart, Yaoliang Yu
• Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks Grant Rotskoff, Eric Vanden-Eijnden
• Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies Sungryull Sohn, Junhyuk Oh, Honglak Lee
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks Kimin Lee, Kibok Lee, Honglak Lee, Jinwoo Shin
• End-to-End Differentiable Physics for Learning and Control Filipe de Avila Belbute-Peres, Kevin Smith, Kelsey Allen, Josh Tenenbaum, J. Zico Kolter
• BRUNO: A Deep Recurrent Model for Exchangeable Data Iryna Korshunova, Jonas Degrave, Ferenc Huszar, Yarin Gal, Arthur Gretton, Joni Dambre
• Stimulus domain transfer in recurrent models for large scale cortical population prediction on video Fabian Sinz, Alexander S. Ecker, Paul Fahey, Edgar Walker, Erick Cobos, Emmanouil Froudarakis, Dimitri Yatsenko, Zachary Pitkow, Jacob Reimer, Andreas Tolias
• Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction Roei Herzig, Moshiko Raboh, Gal Chechik, Jonathan Berant, Amir Globerson
• Distributed Multi-Player Bandits - a Game of Thrones Approach Ilai Bistritz, Amir Leshem
• Efficient Loss-Based Decoding on Graphs for Extreme Classification Itay Evron, Edward Moroshko, Koby Crammer
• Chaining Mutual Information and Tightening Generalization Bounds Amir Asadi, Emmanuel Abbe, Sergio Verdu
• Implicit Probabilistic Integrators for ODEs Onur Teymur, Han Cheng Lie, Tim Sullivan, Ben Calderhead
• Learning Attentional Communication for Multi-Agent Cooperation Jiechuan Jiang, Zongqing Lu
• Training Deep Models Faster with Robust, Approximate Importance Sampling Tyler B. Johnson, Carlos Guestrin
• Bandit Learning with Implicit Feedback Yi Qi, Qingyun Wu, Hongning Wang, Jie Tang, Maosong Sun
• Unsupervised Text Style Transfer using Language Models as Discriminators Zichao Yang, Zhiting Hu, Chris Dyer, Eric P. Xing, Taylor Berg-Kirkpatrick
• Relational recurrent neural networks Adam Santoro, Ryan Faulkner, David Raposo, Jack Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy Lillicrap
• Streaming Kernel PCA with \tilde{O}(\sqrt{n}) Random Features Md Enayat Ullah, Poorya Mianjy, Teodor Vanislavov Marinov, Raman Arora
• REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis Yu-Shao Peng, Kai-Fu Tang, Hsuan-Tien Lin, Edward Chang
• Bayesian Model-Agnostic Meta-Learning Jaesik Yoon, Taesup Kim, Ousmane Dia, Sungwoong Kim, Yoshua Bengio, Sungjin Ahn
• Disconnected Manifold Learning for Generative Adversarial Networks Mahyar Khayatkhoei, Maneesh K. Singh, Ahmed Elgammal
• Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces Yu-An Chung, Wei-Hung Weng, Schrasing Tong, James Glass
• Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem Victor-Emmanuel Brunel
• Out-of-Distribution Detection using Multiple Semantic Label Representations Gabi Shalev, Yossi Adi, Joseph Keshet
• Stochastic Chebyshev Gradient Descent for Spectral Optimization Insu Han, Haim Avron, Jinwoo Shin
• Revisiting (\epsilon, \gamma, \tau)-similarity learning for domain adaptation Sofiane Dhouib, Ievgen Redko
• How to tell when a clustering is (approximately) correct using convex relaxations Marina Meila
• Constant Regret, Generalized Mixability, and Mirror Descent Zakaria Mhammedi, Robert C. Williamson
• A Bayesian Approach to Generative Adversarial Imitation Learning Wonseok Jeon, Seokin Seo, Kee-Eung Kim
• Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis Alyson K. Fletcher, Parthe Pandit, Sundeep Rangan, Subrata Sarkar, Philip Schniter
• Constrained Cross-Entropy Method for Safe Reinforcement Learning Min Wen, Ufuk Topcu
• Multi-Agent Generative Adversarial Imitation Learning Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon
• Adaptive Learning with Unknown Information Flows Yonatan Gur, Ahmadreza Momeni
• Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks Bryan Lim
• Generative modeling for protein structures Namrata Anand, Possu Huang
• Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes
• Knowledge Distillation by On-the-Fly Native Ensemble xu lan, Xiatian Zhu, Shaogang Gong
• Non-Adversarial Mapping with VAEs Yedid Hoshen
• Generalisation in humans and deep neural networks Robert Geirhos, Carlos R. M. Temme, Jonas Rauber, Heiko H. Schütt, Matthias Bethge, Felix A. Wichmann
• Towards Text Generation with Adversarially Learned Neural Outlines Sandeep Subramanian, Sai Rajeswar Mudumba, Alessandro Sordoni, Adam Trischler, Aaron C. Courville, Chris Pal
• cpSGD: Communication-efficient and differentially-private distributed SGD Naman Agarwal, Ananda Theertha Suresh, Felix Xinnan X. Yu, Sanjiv Kumar, Brendan McMahan
• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration Jacob Gardner, Geoff Pleiss, Kilian Q. Weinberger, David Bindel, Andrew G. Wilson
• Diffusion Maps for Textual Network Embedding Xinyuan Zhang, Yitong Li, Dinghan Shen, Lawrence Carin
• Simple, Distributed, and Accelerated Probabilistic Programming Dustin Tran, Matthew W. Hoffman, Dave Moore, Christopher Suter, Srinivas Vasudevan, Alexey Radul
• VideoCapsuleNet: A Simplified Network for Action Detection Kevin Duarte, Yogesh Rawat, Mubarak Shah
• Rectangular Bounding Process Xuhui Fan, Bin Li, Scott SIsson
• Improved Algorithms for Collaborative PAC Learning Huy Nguyen, Lydia Zakynthinou
• Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding Nan Rosemary Ke, Anirudh Goyal ALIAS PARTH GOYAL, Olexa Bilaniuk, Jonathan Binas, Michael C. Mozer, Chris Pal, Yoshua Bengio
• Communication Compression for Decentralized Training Hanlin Tang, Shaoduo Gan, Ce Zhang, Tong Zhang, Ji Liu
• Depth-Limited Solving for Imperfect-Information Games Noam Brown, Tuomas Sandholm, Brandon Amos
• Training Deep Neural Networks with 8-bit Floating Point Numbers Naigang Wang, Jungwook Choi, Daniel Brand, Chia-Yu Chen, Kailash Gopalakrishnan
• Scalar Posterior Sampling with Applications Georgios Theocharous, Zheng Wen, Yasin Abbasi, Nikos Vlassis
• Understanding Batch Normalization Nils Bjorck, Carla P. Gomes, Bart Selman, Kilian Q. Weinberger
• Adversarial Scene Editing: Automatic Object Removal from Weak Supervision Rakshith R. Shetty, Mario Fritz, Bernt Schiele
• Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples Guanhong Tao, Shiqing Ma, Yingqi Liu, Xiangyu Zhang
• On Neuronal Capacity Pierre Baldi, Roman Vershynin
• Breaking the Activation Function Bottleneck through Adaptive Parameterization Sebastian Flennerhag, Hujun Yin, John Keane, Mark Elliot
• Learning Loop Invariants for Program Verification Xujie Si, Hanjun Dai, Mukund Raghothaman, Mayur Naik, Le Song
• Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization Bruno Korbar, Du Tran, Lorenzo Torresani
• Towards Robust Interpretability with Self-Explaining Neural Networks David Alvarez Melis, Tommi Jaakkola
• Deep State Space Models for Time Series Forecasting Syama Sundar Rangapuram, Matthias W. Seeger, Jan Gasthaus, Lorenzo Stella, Yuyang Wang, Tim Januschowski
• Constrained Graph Variational Autoencoders for Molecule Design Qi Liu, Miltiadis Allamanis, Marc Brockschmidt, Alexander Gaunt
• Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction Kevin Ellis, Lucas Morales, Mathias Sablé-Meyer, Armando Solar-Lezama, Josh Tenenbaum
• Neural Architecture Optimization Renqian Luo, Fei Tian, Tao Qin, Enhong Chen, Tie-Yan Liu
• Preference Based Adaptation for Learning Objectives Yao-Xiang Ding, Zhi-Hua Zhou
• Distributed k-Clustering for Data with Heavy Noise Shi Li, Xiangyu Guo
• Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte CarloHOLDEN LEE, Andrej Risteski, Rong Ge
• A General Method for Amortizing Variational Filtering Joseph Marino, Milan Cvitkovic, Yisong Yue
• A Reduction for Efficient LDA Topic Reconstruction Matteo Almanza, Flavio Chierichetti, Alessandro Panconesi, Andrea Vattani
• Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data Dominik Linzner, Heinz Koeppl
• RenderNet: A deep convolutional network for differentiable rendering from 3D shapes Thu H. Nguyen-Phuoc, Chuan Li, Stephen Balaban, Yongliang Yang
• Robust Hypothesis Testing Using Wasserstein Uncertainty Sets RUI GAO, Liyan Xie, Yao Xie, Huan Xu
• Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks Zhihao Zheng, Pengyu Hong
• Monte-Carlo Tree Search for Constrained POMDPs Jongmin Lee, Geon-hyeong Kim, Pascal Poupart, Kee-Eung Kim
• Learning to Repair Software Vulnerabilities with Generative Adversarial Networks Jacob Harer, Onur Ozdemir, Tomo Lazovich, Christopher Reale, Rebecca Russell, Louis Kim, peter chin
• Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation Tianyu He, Xu Tan, Yingce Xia, Di He, Tao Qin, Zhibo Chen, Tie-Yan Liu
• Dirichlet belief networks for topic structure learning He Zhao, Lan Du, Wray Buntine, Mingyuan Zhou
• Stochastic Expectation Maximization with Variance Reduction Jianfei Chen, Jun Zhu, Yee Whye Teh, Tong Zhang
• Submodular Maximization via Gradient Ascent: The Case of Deep Submodular Functions Wenruo Bai, William Stafford Noble, Jeff A. Bilmes
• The challenge of realistic music generation: modelling raw audio at scale Sander Dieleman, Aaron van den Oord, Karen Simonyan
• Spectral Signatures in Backdoor Attacks Brandon Tran, Jerry Li, Aleksander Madry
• Reward learning from human preferences and demonstrations in Atari Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, Dario Amodei
• Approximate Knowledge Compilation by Online Collapsed Importance Sampling Tal Friedman, Guy Van den Broeck
• Neural Arithmetic Logic Units Andrew Trask, Felix Hill, Scott E. Reed, Jack Rae, Chris Dyer, Phil Blunsom
• Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training Youjie Li, Mingchao Yu, Songze Li, Salman Avestimehr, Nam Sung Kim, Alexander Schwing
• Improved Expressivity Through Dendritic Neural Networks Xundong Wu, Xiangwen Liu, Wei Li, Qing Wu
• Efficient Anomaly Detection via Matrix Sketching Vatsal Sharan, Parikshit Gopalan, Udi Wieder
• Learning to Specialize with Knowledge Distillation for Visual Question Answering Jonghwan Mun, Kimin Lee, Jinwoo Shin, Bohyung Han
• A Lyapunov-based Approach to Safe Reinforcement Learning Yinlam Chow, Ofir Nachum, Edgar Duenez-Guzman, Mohammad Ghavamzadeh
• Credit Assignment For Collective Multiagent RL With Global Rewards Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau
• Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes Loucas Pillaud-Vivien, Alessandro Rudi, Francis Bach
• Does mitigating ML's impact disparity require treatment disparity? Zachary Lipton, Julian McAuley, Alexandra Chouldechova
• Proximal Graphical Event Models Debarun Bhattacharjya, Dharmashankar Subramanian, Tian Gao
• Bayesian Control of Large MDPs with Unknown Dynamics in Data-Poor Environments Mahdi Imani, Seyede Fatemeh Ghoreishi, Ulisses M. Braga-Neto
• Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data Yuanzhi Li, Yingyu Liang
• Hamiltonian Variational Auto-Encoder Anthony L. Caterini, Arnaud Doucet, Dino Sejdinovic
• Modelling and unsupervised learning of symmetric deformable object categories James Thewlis, Hakan Bilen, Andrea Vedaldi
• Graphical model inference: Sequential Monte Carlo meets deterministic approximations Fredrik Lindsten, Jouni Helske, Matti Vihola
• Statistical mechanics of low-rank tensor decomposition Jonathan Kadmon, Surya Ganguli
• Variational Bayesian Monte Carlo Luigi Acerbi
• Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion Jacob Buckman, Danijar Hafner, George Tucker, Eugene Brevdo, Honglak Lee
• Efficient Online Portfolio with Logarithmic Regret Haipeng Luo, Chen-Yu Wei, Kai Zheng
• Algorithms and Theory for Multiple-Source Adaptation Judy Hoffman, Mehryar Mohri, Ningshan Zhang
• Online Reciprocal Recommendation with Theoretical Performance Guarantees Claudio Gentile, Nikos Parotsidis, Fabio Vitale
• The promises and pitfalls of Stochastic Gradient Langevin Dynamics Nicolas Brosse, Alain Durmus, Eric Moulines
• How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective Lei Wu, Chao Ma, Weinan E
• Differentiable MPC for End-to-end Planning and Control Brandon Amos, Ivan Jimenez, Jacob Sacks, Byron Boots, J. Zico Kolter
• Bilevel learning of the Group Lasso structure Jordan Frecon, Saverio Salzo, Massimiliano Pontil
• Constructing Unrestricted Adversarial Examples with Generative Models Yang Song, Rui Shu, Nate Kushman, Stefano Ermon
• Information-theoretic Limits for Community Detection in Network Models Chuyang Ke, Jean Honorio
• Learning Conditioned Graph Structures for Interpretable Visual Question Answering Will Norcliffe-Brown, Stathis Vafeias, Sarah Parisot
• Distributionally Robust Graphical Models Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri, Xinhua Zhang, Brian Ziebart
• Transfer Learning with Neural AutoML Catherine Wong, Neil Houlsby, Yifeng Lu, Andrea Gesmundo
• Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity Conghui Tan, Tong Zhang, Shiqian Ma, Ji Liu
• On preserving non-discrimination when combining expert advice Avrim Blum, Suriya Gunasekar, Thodoris Lykouris, Nati Srebro
• Learning to Play With Intrinsically-Motivated, Self-Aware Agents Nick Haber, Damian Mrowca, Stephanie Wang, Li F. Fei-Fei, Daniel L. Yamins
• Scaling provable adversarial defenses Eric Wong, Frank Schmidt, Jan Hendrik Metzen, J. Zico Kolter
• Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images Andrei Zanfir, Elisabeta Marinoiu, Mihai Zanfir, Alin-Ionut Popa, Cristian Sminchisescu
• Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs Han Shao, Xiaotian Yu, Irwin King, Michael R. Lyu
• Data-dependent PAC-Bayes priors via differential privacy Gintare Karolina Dziugaite, Daniel M. Roy
• Deep Poisson gamma dynamical systems Dandan Guo, Bo Chen, Hao Zhang, Mingyuan Zhou
• Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds Kry Lui, Gavin Weiguang Ding, Ruitong Huang, Robert McCann
• Teaching Inverse Reinforcement Learners via Features and Demonstrations Luis Haug, Sebastian Tschiatschek, Adish Singla
• Wasserstein Distributionally Robust Kalman Filtering Soroosh Shafieezadeh Abadeh, Viet Anh Nguyen, Daniel Kuhn, Peyman Mohajerin Mohajerin Esfahani
• Generalisation of structural knowledge in the hippocampal-entorhinal system James Whittington, Timothy Muller, Shirely Mark, Caswell Barry, Tim Behrens
• Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization Blake E. Woodworth, Jialei Wang, Adam Smith, Brendan McMahan, Nati Srebro
• Adversarial Regularizers in Inverse Problems Sebastian Lunz, Carola Schoenlieb, Ozan Öktem
• Clustering Redemption–Beyond the Impossibility of Kleinberg’s Axioms Vincent Cohen-Addad, Varun Kanade, Frederik Mallmann-Trenn
• Co-teaching: Robust training of deep neural networks with extremely noisy labels Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, Masashi Sugiyama
• Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition Justin Fu, Avi Singh, Dibya Ghosh, Larry Yang, Sergey Levine
• A convex program for bilinear inversion of sparse vectors Alireza Aghasi, Ali Ahmed, Paul Hand, Babhru Joshi
• Adversarial Multiple Source Domain Adaptation Han Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura, Joao P. Costeira, Geoffrey J. Gordon
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks Arthur Jacot, Franck Gabriel, Clement Hongler
• Contextual Stochastic Block Models Yash Deshpande, Subhabrata Sen, Andrea Montanari, Elchanan Mossel
• A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks Jeffrey Chan, Valerio Perrone, Jeffrey Spence, Paul Jenkins, Sara Mathieson, Yun Song
• Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects Adam Kosiorek, Hyunjik Kim, Yee Whye Teh, Ingmar Posner
• Randomized Prior Functions for Deep Reinforcement Learning Ian Osband, John Aslanides, Albin Cassirer
• Compact Representation of Uncertainty in Clustering Craig Greenberg, Nicholas Monath, Ari Kobren, Patrick Flaherty, Andrew McGregor, Andrew McCallum
• Learning without the Phase: Regularized PhaseMax Achieves Optimal Sample Complexity Fariborz Salehi, Ehsan Abbasi, Babak Hassibi
• Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages Michelle Yuan, Benjamin Van Durme, Jordan L. Ying
• Estimators for Multivariate Information Measures in General Probability Spaces Arman Rahimzamani, Himanshu Asnani, Pramod Viswanath, Sreeram Kannan
• DeepPINK: reproducible feature selection in deep neural networks Yang Lu, Yingying Fan, Jinchi Lv, William Stafford Noble
• HOUDINI: Lifelong Learning as Program Synthesis Lazar Valkov, Dipak Chaudhari, Akash Srivastava, Charles Sutton, Swarat Chaudhuri
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction Liang-Chieh Chen, Maxwell Collins, Yukun Zhu, George Papandreou, Barret Zoph, Florian Schroff, Hartwig Adam, Jon Shlens
• Orthogonally Decoupled Variational Gaussian Processes Hugh Salimbeni, Ching-An Cheng, Byron Boots, Marc Deisenroth
• Dendritic cortical microcircuits approximate the backpropagation algorithm João Sacramento, Rui Ponte Costa, Yoshua Bengio, Walter Senn
• Learning Plannable Representations with Causal InfoGAN Thanard Kurutach, Aviv Tamar, Ge Yang, Stuart J. Russell, Pieter Abbeel
• Uniform Convergence of Gradients for Non-Convex Learning and Optimization Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
• Automatic differentiation in ML: Where we are and where we should be going Bart van Merrienboer, Olivier Breuleux, Arnaud Bergeron, Pascal Lamblin
• A Bayesian Nonparametric View on Count-Min Sketch Diana Cai, Michael Mitzenmacher, Ryan P. Adams
• Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels Zhilu Zhang, Mert Sabuncu
• Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry P. Vetrov, Andrew G. Wilson
• Flexible neural representation for physics prediction Damian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Li F. Fei-Fei, Josh Tenenbaum, Daniel L. Yamins
• Legendre Decomposition for Tensors Mahito Sugiyama, Hiroyuki Nakahara, Koji Tsuda
• Reinforcement Learning of Theorem Proving Cezary Kaliszyk, Josef Urban, Henryk Michalewski, Miroslav Olšák
• Data Amplification: A Unified and Competitive Approach to Property Estimation Yi HAO, Alon Orlitsky, Ananda Theertha Suresh, Yihong Wu
• Group Equivariant Capsule Networks Jan Eric Lenssen, Matthias Fey, Pascal Libuschewski
• Stein Variational Gradient Descent as Moment Matching Qiang Liu, Dilin Wang
• Differential Privacy for Growing Databases Rachel Cummings, Sara Krehbiel, Kevin A. Lai, Uthaipon Tantipongpipat
• Exploration in Structured Reinforcement Learning Jungseul Ok, Alexandre Proutiere, Damianos Tranos
• A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite Matrices Rudrasis Chakraborty, Chun-Hao Yang, Xingjian Zhen, Monami Banerjee, Derek Archer, David Vaillancourt, Vikas Singh, Baba Vemuri
• Balanced Policy Evaluation and Learning Nathan Kallus
• Distributed Multitask Reinforcement Learning with Quadratic Convergence Rasul Tutunov, Dongho Kim, Haitham Bou Ammar
• Improving Neural Program Synthesis with Inferred Execution Traces Richard Shin, Illia Polosukhin, Dawn Song
• Adaptive Path-Integral Autoencoders: Representation Learning and Planning for Dynamical Systems Jung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park, Han-Lim Choi
• Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes Andrea Tirinzoni, Marek Petrik, Xiangli Chen, Brian Ziebart
• GLoMo: Unsupervised Learning of Transferable Relational Graphs Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He, William W. Cohen, Ruslan R. Salakhutdinov, Yann LeCun
• Online Learning of Quantum States Scott Aaronson, Xinyi Chen, Elad Hazan, Satyen Kale, Ashwin Nayak
• Wavelet regression and additive models for irregularly spaced data Asad Haris, Ali Shojaie, Noah Simon
• Inferring Latent Velocities from Weather Radar Data using Gaussian Processes Rico Angell, Daniel R. Sheldon
• A Structured Prediction Approach for Label Ranking Anna Korba, Alexandre Garcia, Florence d'Alché-Buc
• Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features Mojmir Mutny, Andreas Krause
• FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma
• Reversible Recurrent Neural Networks Matthew MacKay, Paul Vicol, Jimmy Ba, Roger B. Grosse
• SING: Symbol-to-Instrument Neural Generator Alexandre Defossez, Neil Zeghidour, Nicolas Usunier, Leon Bottou, Francis Bach
• Learning Compressed Transforms with Low Displacement Rank Anna Thomas, Albert Gu, Tri Dao, Atri Rudra, Christopher Ré
• Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds Xiaohan Chen, Jialin Liu, Zhangyang Wang, Wotao Yin
• Iterative Value-Aware Model Learning Amir-massoud Farahmand
• Invariant Representations without Adversarial Training Daniel Moyer, Shuyang Gao, Rob Brekelmans, Aram Galstyan, Greg Ver Steeg
• Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias Abhinav Gupta, Adithyavairavan Murali, Dhiraj Prakashchand Gandhi, Lerrel Pinto
• Learning Safe Policies with Expert Guidance Jessie Huang, Fa Wu, Doina Precup, Yang Cai
• Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data Ehsan Hajiramezanali, Siamak Zamani Dadaneh, Alireza Karbalayghareh, Mingyuan Zhou, Xiaoning Qian
• Learning SMaLL Predictors Vikas Garg, Ofer Dekel, Lin Xiao
• Phase Retrieval Under a Generative Prior Paul Hand, Oscar Leong, Vlad Voroninski
• Quadrature-based features for kernel approximation Marina Munkhoeva, Yermek Kapushev, Evgeny Burnaev, Ivan Oseledets
• Reducing Network Agnostophobia Akshay Raj Dhamija, Manuel Günther, Terrance Boult
• A Stein variational Newton method Gianluca Detommaso, Tiangang Cui, Youssef Marzouk, Alessio Spantini, Robert Scheichl
• Watch Your Step: Learning Node Embeddings via Graph Attention Sami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou, Alexander A. Alemi
• Visual Reinforcement Learning with Imagined Goals Ashvin V. Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, Sergey Levine
• Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition Kuan Han, Haiguang Wen, Yizhen Zhang, Di Fu, Eugenio Culurciello, Zhongming Liu
• PAC-Bayes bounds for stable algorithms with instance-dependent priors Omar Rivasplata, Csaba Szepesvari, John S. Shawe-Taylor, Emilio Parrado-Hernandez, Shiliang Sun
• Beyond Grids: Learning Graph Representations for Visual Recognition Yin Li, Abhinav Gupta
• The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization Constantinos Daskalakis, Ioannis Panageas
• Coordinate Descent with Bandit Sampling Farnood Salehi, Patrick Thiran, Elisa Celis
• Deep Dynamical Modeling and Control of Unsteady Fluid Flows Jeremy Morton, Antony Jameson, Mykel J. Kochenderfer, Freddie Witherden
• Confounding-Robust Policy Improvement Nathan Kallus, Angela Zhou
• The Importance of Sampling inMeta-Reinforcement Learning Bradly Stadie, Ge Yang, Rein Houthooft, Peter Chen, Yan Duan, Yuhuai Wu, Pieter Abbeel, Ilya Sutskever
• Representer Point Selection for Explaining Deep Neural Networks Chih-Kuan Yeh, Joon Kim, Ian En-Hsu Yen, Pradeep K. Ravikumar
• The Effect of Network Width on the Performance of Large-batch Training Lingjiao Chen, Hongyi Wang, Jinman Zhao, Dimitris Papailiopoulos, Paraschos Koutris
• SNIPER: Efficient Multi-Scale Training Bharat Singh, Mahyar Najibi, Larry S. Davis
• The Sample Complexity of Semi-Supervised Learning with Nonparametric Mixture Models Chen Dan, Liu Leqi, Bryon Aragam, Pradeep K. Ravikumar, Eric P. Xing
• Hardware Conditioned Policies for Multi-Robot Transfer Learning Tao Chen, Adithyavairavan Murali, Abhinav Gupta
• Co-regularized Alignment for Unsupervised Domain Adaptation Abhishek Kumar, Prasanna Sattigeri, Kahini Wadhawan, Leonid Karlinsky, Rogerio Feris, Bill Freeman, Gregory Wornell
• Statistical and Computational Trade-Offs in Kernel K-Means Daniele Calandriello, Lorenzo Rosasco
• Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures Sergey Bartunov, Adam Santoro, Blake Richards, Luke Marris, Geoffrey E. Hinton, Timothy Lillicrap
• Learning Attractor Dynamics for Generative Memory Yan Wu, Gregory Wayne, Karol Gregor, Timothy Lillicrap
• The emergence of multiple retinal cell types through efficient coding of natural movies Samuel Ocko, Jack Lindsey, Surya Ganguli, Stephane Deny
• Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Andrea Vedaldi
• The Global Anchor Method for Quantifying Linguistic Shifts and Domain Adaptation Zi Yin, Vin Sachidananda, Balaji Prabhakar
• Identification and Estimation of Causal Effects from Dependent Data Eli Sherman, Ilya Shpitser
• Deepcode: Feedback Codes via Deep Learning Hyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
• Learning and Testing Causal Models with Interventions Jayadev Acharya, Arnab Bhattacharyya, Constantinos Daskalakis, Saravanan Kandasamy
• Implicit Bias of Gradient Descent on Linear Convolutional Networks Suriya Gunasekar, Jason D. Lee, Daniel Soudry, Nati Srebro
• DAGs with NO TEARS: Continuous Optimization for Structure Learning Xun Zheng, Bryon Aragam, Pradeep K. Ravikumar, Eric P. Xing
• PAC-Bayes Tree: weighted subtrees with guarantees Tin D. Nguyen, Samory Kpotufe
• Multi-objective Maximization of Monotone Submodular Functions with Cardinality Constraint Rajan Udwani
• Sanity Checks for Saliency Maps Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim
• Probabilistic Model-Agnostic Meta-Learning Chelsea Finn, Kelvin Xu, Sergey Levine
• Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
• e-SNLI: Natural Language Inference with Natural Language Explanations Oana-Maria Camburu, Tim Rocktäschel, Thomas Lukasiewicz, Phil Blunsom
• Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis Thomas George, César Laurent, Xavier Bouthillier, Nicolas Ballas, Pascal Vincent
• Learning convex bounds for linear quadratic control policy synthesis Jack Umenberger, Thomas B. Schön
• Neural Proximal Gradient Descent for Compressive Imaging Morteza Mardani, Qingyun Sun, David Donoho, Vardan Papyan, Hatef Monajemi, Shreyas Vasanawala, John Pauly
• Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation Liwei Wang, Lunjia Hu, Jiayuan Gu, Zhiqiang Hu, Yue Wu, Kun He, John Hopcroft
• Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization Rad Niazadeh, Tim Roughgarden, Joshua Wang
• An intriguing failing of convolutional neural networks and the CoordConv solution Rosanne Liu, Joel Lehman, Piero Molino, Felipe Petroski Such, Eric Frank, Alex Sergeev, Jason Yosinski
• Trading robust representations for sample complexity through self-supervised visual experience Andrea Tacchetti, Stephen Voinea, Georgios Evangelopoulos
• Invertibility of Convolutional Generative Networks from Partial Measurements Fangchang Ma, Ulas Ayaz, Sertac Karaman
• Ex ante coordination and collusion in zero-sum multi-player extensive-form games Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm
• Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization Hoi-To Wai, Zhuoran Yang, Princeton Zhaoran Wang, Mingyi Hong
• Improving Online Algorithms via ML Predictions Manish Purohit, Zoya Svitkina, Ravi Kumar
• Global Non-convex Optimization with Discretized Diffusions Murat A. Erdogdu, Lester Mackey, Ohad Shamir
• Theoretical guarantees for EM under misspecified Gaussian mixture models Raaz Dwivedi, nhật Hồ, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan
• Coupled Variational Bayes via Optimization Embedding Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song
• Improving Explorability in Variational Inference with Annealed Variational Objectives Chin-Wei Huang, Shawn Tan, Alexandre Lacoste, Aaron C. Courville
• Latent Alignment and Variational Attention Yuntian Deng, Yoon Kim, Justin Chiu, Demi Guo, Alexander Rush
• Towards Deep Conversational Recommendations Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, Chris Pal
• Unsupervised Depth Estimation, 3D Face Rotation and Replacement Joel Ruben Antony Moniz, Christopher Beckham, Simon Rajotte, Sina Honari, Chris Pal
• Generalization Bounds for Uniformly Stable Algorithms Vitaly Feldman, Jan Vondrak
• Deep Anomaly Detection Using Geometric Transformations Izhak Golan, Ran El-Yaniv
• Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport Theo Lacombe, Marco Cuturi, Steve OUDOT
• Entropy Rate Estimation for Markov Chains with Large State Space Yanjun Han, Jiantao Jiao, Chuan-Zheng Lee, Tsachy Weissman, Yihong Wu, Tiancheng Yu
• Adaptive Methods for Nonconvex Optimization Manzil Zaheer, Sashank Reddi, Devendra Sachan, Satyen Kale, Sanjiv Kumar
• Object-Oriented Dynamics Predictor Guangxiang Zhu, Zhiao Huang, Chongjie Zhang
• Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models Alexander Neitz, Giambattista Parascandolo, Stefan Bauer, Bernhard Schölkopf
• Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation Matthew O'Kelly, Aman Sinha, Hongseok Namkoong, Russ Tedrake, John C. Duchi
• Reinforcement Learning for Solving the Vehicle Routing Problem MohammadReza Nazari, Afshin Oroojlooy, Lawrence Snyder, Martin Takac
• ATOMO: Communication-efficient Learning via Atomic Sparsification Hongyi Wang, Scott Sievert, Shengchao Liu, Zachary Charles, Dimitris Papailiopoulos, Stephen Wright
• Dynamic Network Model from Partial Observations Elahe Ghalebi, Baharan Mirzasoleiman, Radu Grosu, Jure Leskovec
• Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies Alessandro Achille, Tom Eccles, Loic Matthey, Chris Burgess, Nicholas Watters, Alexander Lerchner, Irina Higgins
• Maximizing acquisition functions for Bayesian optimization James Wilson, Frank Hutter, Marc Deisenroth
• On Markov Chain Gradient Descent Tao Sun, Yuejiao Sun, Wotao Yin
• Variance-Reduced Stochastic Gradient Descent on Streaming Data Ellango Jothimurugesan, Ashraf Tahmasbi, Phillip Gibbons, Srikanta Tirthapura
• Online Robust Policy Learning in the Presence of Unknown Adversaries Aaron Havens, Zhanhong Jiang, Soumik Sarkar
• Uplift Modeling from Separate Labels Ikko Yamane, Florian Yger, Jamal Atif, Masashi Sugiyama
• Learning Invariances using the Marginal Likelihood Mark van der Wilk, Matthias Bauer, ST John, James Hensman
• Non-delusional Q-learning and value-iteration Tyler Lu, Dale Schuurmans, Craig Boutilier
• Using Large Ensembles of Control Variates for Variational Inference Tomas Geffner, Justin Domke
• Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization Yuanxiang Gao, Li Chen, Baochun Li
• Learning to Reason with Third Order Tensor Products Imanol Schlag, Jürgen Schmidhuber
• Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing Chen Liang, Mohammad Norouzi, Jonathan Berant, Quoc V. Le, Ni Lao
• Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams Tam Le, Makoto Yamada
• Neural Voice Cloning with a Few Samples Sercan Arik, Jitong Chen, Kainan Peng, Wei Ping, Yanqi Zhou
• Blind Deconvolutional Phase Retrieval via Convex Programming Ali Ahmed, Alireza Aghasi, Paul Hand
• Scalable Laplacian K-modes Imtiaz Ziko, Eric Granger, Ismail Ben Ayed
• A Retrieve-and-Edit Framework for Predicting Structured Outputs Tatsunori B. Hashimoto, Kelvin Guu, Yonatan Oren, Percy S. Liang
• Testing for Families of Distributions via the Fourier Transform Alistair Stewart, Ilias Diakonikolas, Clement Canonne
• Thwarting Adversarial Examples: An L_0-Robust Sparse Fourier Transform Mitali Bafna, Jack Murtagh, Nikhil Vyas
• Blockwise Parallel Decoding for Deep Autoregressive Models Mitchell Stern, Noam Shazeer, Jakob Uszkoreit
• Low-Rank Tucker Decomposition of Large Tensors Using TensorSketch Osman Asif Malik, Stephen Becker
• A Simple Cache Model for Image Recognition Emin Orhan
• Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network Risi Kondor, Zhen Lin, Shubhendu Trivedi
• Bayesian Nonparametric Spectral Estimation Felipe Tobar
• A Spectral View of Adversarially Robust Features Shivam Garg, Vatsal Sharan, Brian Zhang, Gregory Valiant
• Synaptic Strength For Convolutional Neural Network CHEN LIN, Zhao Zhong, Wu Wei, Junjie Yan
• Human-in-the-Loop Interpretability Prior Isaac Lage, Andrew Ross, Samuel J. Gershman, Been Kim, Finale Doshi-Velez
• Learning To Learn Around A Common Mean Giulia Denevi, Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil
• Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming Fei Wang, James Decker, Xilun Wu, Gregory Essertel, Tiark Rompf
• Learning with SGD and Random Features Luigi Carratino, Alessandro Rudi, Lorenzo Rosasco
• Total stochastic gradient algorithms and applications in reinforcement learning Paavo Parmas
• Glow: Generative Flow with Invertible 1x1 Convolutions Durk P. Kingma, Prafulla Dhariwal
• Nonparametric Density Estimation under Adversarial Losses Shashank Singh, Ananya Uppal, Boyue Li, Chun-Liang Li, Manzil Zaheer, Barnabas Poczos
• Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions Boris Muzellec, Marco Cuturi
• Learning to Share and Hide Intentions using Information Regularization DJ Strouse, Max Kleiman-Weiner, Josh Tenenbaum, Matt Botvinick, David J. Schwab
• Predictive Approximate Bayesian Computation via Saddle Points Yingxiang Yang, Bo Dai, Negar Kiyavash, Niao He
• Robustness of conditional GANs to noisy labels Kiran K. Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh
• Robust Learning of Fixed-Structure Bayesian Networks Yu Cheng, Ilias Diakonikolas, Daniel Kane, Alistair Stewart
• Improving Simple Models with Confidence Profiles Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss, Peder A. Olsen
• PCA of high dimensional random walks with comparison to neural network training Joseph Antognini, Jascha Sohl-Dickstein
• Learning to Solve SMT Formulas Mislav Balunovic, Pavol Bielik, Martin Vechev
• Lifted Weighted Mini-Bucket Nicholas Gallo, Alexander T. Ihler
• Learning and Inference in Hilbert Space with Quantum Graphical Models Siddarth Srinivasan, Carlton Downey, Byron Boots
• Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound Hadi Kazemi, Sobhan Soleymani, Fariborz Taherkhani, Seyed Iranmanesh, Nasser Nasrabadi
• Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution Dimitrios Diochnos, Saeed Mahloujifar, Mohammad Mahmoody
• Gaussian Process Prior Variational Autoencoders Francesco Paolo Casale, Adrian Dalca, Luca Saglietti, Jennifer Listgarten, Nicolo Fusi
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data Maurice Weiler, Mario Geiger, Max Welling, Wouter Boomsma, Taco Cohen
• Context-aware Synthesis and Placement of Object Instances Donghoon Lee, Sifei Liu, Jinwei Gu, Ming-Yu Liu, Ming-Hsuan Yang, Jan Kautz
• Convex Elicitation of Continuous Properties Jessica Finocchiaro, Rafael Frongillo
• Mesh-TensorFlow: Deep Learning for Supercomputers Noam Shazeer, Youlong Cheng, Niki Parmar, Dustin Tran, Ashish Vaswani, Penporn Koanantakool, Peter Hawkins, HyoukJoong Lee, Mingsheng Hong, Cliff Young, Ryan Sepassi, Blake Hechtman
• Learning Abstract Options Matthew Riemer, Miao Liu, Gerald Tesauro
• Bounded-Loss Private Prediction Markets Rafael Frongillo, Bo Waggoner
• Temporal alignment and latent Gaussian process factor inference in population spike trains Lea Duncker, Maneesh Sahani
• Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise Dan Hendrycks, Mantas Mazeika, Duncan Wilson, Kevin Gimpel
• Discretely Relaxing Continuous Variables for tractable Variational Inference Trefor Evans, Prasanth Nair
• Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior Zi Wang, Beomjoon Kim, Leslie Pack Kaelbling
• Diversity-Driven Exploration Strategy for Deep Reinforcement Learning Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Tsu-Jui Fu, Chun-Yi Lee
• Deep Generative Models with Learnable Knowledge Constraints Zhiting Hu, Zichao Yang, Ruslan R. Salakhutdinov, LIANHUI Qin, Xiaodan Liang, Haoye Dong, Eric P. Xing
• The Sparse Manifold Transform Yubei Chen, Dylan Paiton, Bruno Olshausen
• Bayesian Structure Learning by Recursive Bootstrap Raanan Y. Rohekar, Yaniv Gurwicz, Shami Nisimov, Guy Koren, Gal Novik
• Complex Gated Recurrent Neural Networks Moritz Wolter, Angela Yao
• Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders Abubakar Abid, James Y. Zou
• Streamlining Variational Inference for Constraint Satisfaction Problems Aditya Grover, Tudor Achim, Stefano Ermon
• Fast deep reinforcement learning using online adjustments from the past Steven Hansen, Alexander Pritzel, Pablo Sprechmann, Andre Barreto, Charles Blundell
• Improved Network Robustness with Adversary Critic Alexander Matyasko, Lap-Pui Chau
• Regret Bounds for Online Portfolio Selection with a Cardinality Constraint Shinji Ito, Daisuke Hatano, Sumita Hanna, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken-Ichi Kawarabayashi
• Sketching Method for Large Scale Combinatorial Inference Wei Sun, Junwei Lu, Han Liu
• Connecting Optimization and Regularization Paths Arun Suggala, Adarsh Prasad, Pradeep K. Ravikumar
• Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices Jinhwan Park, Yoonho Boo, Iksoo Choi, Sungho Shin, Wonyong Sung
• Understanding Regularized Spectral Clustering via Graph Conductance Yilin Zhang, Karl Rohe
• Data-Driven Clustering via Parameterized Lloyd's Families Maria-Florina F. Balcan, Travis Dick, Colin White
• Learning Beam Search Policies via Imitation Learning Renato Negrinho, Matthew Gormley, Geoffrey J. Gordon
• Benefits of over-parameterization with EM Ji Xu, Daniel J. Hsu, Arian Maleki
• Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning Rui Luo, Jianhong Wang, Yaodong Yang, Jun WANG, Zhanxing Zhu
• Robust Subspace Approximation in a Stream Roie Levin, Anish Prasad Sevekari, David Woodruff
• Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues Soumendu Sundar Mukherjee, Purnamrita Sarkar, Y. X. Rachel Wang, Bowei Yan
• Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems Yair Carmon, John C. Duchi
• Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Language Matthew D. Hoffman
• DropBlock: A regularization method for convolutional networks Golnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le
• Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger Gabriel Synnaeve, Zeming Lin, Jonas Gehring, Dan Gant, Vegard Mella, Vasil Khalidov, Nicolas Carion, Nicolas Usunier
• With Friends Like These, Who Needs Adversaries? Saumya Jetley, Nicholas Lord, Philip Torr
• Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenters Pavel Dvurechenskii, Darina Dvinskikh, Alexander Gasnikov, Cesar Uribe, Angelia Nedich
• Joint Autoregressive and Hierarchical Priors for Learned Image Compression David Minnen, Johannes Ballé, George D. Toderici
• Learning Temporal Point Processes via Reinforcement Learning Shuang Li, Shuai Xiao, Shixiang Zhu, Nan Du, Yao Xie, Le Song
• Bias and Generalization in Deep Generative Models: An Empirical Study Shengjia Zhao, Hongyu Ren, Arianna Yuan, Jiaming Song, Noah Goodman, Stefano Ermon
• Fast and Effective Robustness Certification Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin Vechev
• Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds Raghav Somani, Chirag Gupta, Prateek Jain, Praneeth Netrapalli
• Differentially Private Change-Point Detection Rachel Cummings, Sara Krehbiel, Yajun Mei, Rui Tuo, Wanrong Zhang
• Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations Tong Wang
• Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions Sara Magliacane, Thijs van Ommen, Tom Claassen, Stephan Bongers, Philip Versteeg, Joris M. Mooij
• Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons Nima Anari, Constantinos Daskalakis, Wolfgang Maass, Christos Papadimitriou, Amin Saberi, Santosh Vempala
• MixLasso: Generalized Mixed Regression via Convex Atomic-Norm Regularization Ian En-Hsu Yen, Wei-Cheng Lee, Kai Zhong, Sung-En Chang, Pradeep K. Ravikumar, Shou-De Lin
• Semidefinite relaxations for certifying robustness to adversarial examples Aditi Raghunathan, Jacob Steinhardt, Percy S. Liang
• Removing Hidden Confounding by Experimental Grounding Nathan Kallus, Aahlad Manas Puli, Uri Shalit
• Topkapi: Parallel and Fast Sketches for Finding Top-K Frequent Elements Ankush Mandal, He Jiang, Anshumali Shrivastava, Vivek Sarkar
• Contrastive Learning from Pairwise Measurements Yi Chen, Zhuoran Yang, Yuchen Xie, Princeton Zhaoran Wang
• Point process latent variable models of larval zebrafish behavior Anuj Sharma, Robert Johnson, Florian Engert, Scott Linderman
• Computationally and statistically efficient learning of causal Bayes nets using path queries Kevin Bello, Jean Honorio
• Sparse PCA from Sparse Linear Regression Guy Bresler, Sung Min Park, Madalina Persu
• Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices Don Dennis, Chirag Pabbaraju, Harsha Vardhan Simhadri, Prateek Jain
• Transfer of Deep Reactive Policies for MDP Planning Aniket (Nick) Bajpai, Sankalp Garg, None
• The Price of Fair PCA: One Extra dimension Samira Samadi, Uthaipon Tantipongpipat, Jamie H. Morgenstern, Mohit Singh, Santosh Vempala
• GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking Patrick Chen, Si Si, Yang Li, Ciprian Chelba, Cho-Jui Hsieh