【NIPS2018】Spotlight及Oral论文汇总

nips2018 spotlight （168篇）和Oral（30篇）是会议中较为出色的论文,（点击论文可以查看对应摘要和链接）

1.Oral

【神经元容量】On Neuronal Capacity
【词嵌入】On the Dimensionality of Word Embedding
【生成先验下的相位恢复问题】Phase Retrieval Under a Generative Prior
【树突皮质微回路结构近似bp算法】Dendritic cortical microcircuits approximate the backpropagation algorithm
【回朔编辑架构生成期望结果】A Retrieve-and-Edit Framework for Predicting Structured Outputs
【谱滤波器学习隐空间线性动力学】Spectral Filtering for General Linear Dynamical Systems
【结构化知识归一化】Generalisation of structural knowledge in the hippocampal-entorhinal system
【参数化隐含层状态】Neural Ordinary Differential Equations
【私有学习】Model-Agnostic Private Learning
【概率群体码】A probabilistic population code based on neural samples
【BN优化】How Does Batch Normalization Help Optimization?
【解可满足性模理论方程】Learning to Solve SMT Formulas add1 add2
【结构化强化学习】Exploration in Structured Reinforcement Learning
【视觉记忆路径回溯】Visual Memory for Robust Path Following
【高斯混合模型样本压缩机制】Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes
【重要性采样优化策略】Policy Optimization via Importance Sampling
【VAE分离源】Isolating Sources of Disentanglement in Variational Autoencoders
【随机立方正则化】Stochastic Cubic Regularization for Fast Nonconvex Optimization
【循环词模型】Recurrent World Models Facilitate Policy Evolution
【离散概率图模型】Approximate Knowledge Compilation by Online Collapsed Importance Sampling
【非凸二次问题】Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems
【整合行为与神经数据】Integrated accounts of behavioral and neuroimaging data using flexible recurrent neural network models
【变分推理】Variational Inference with Tail-adaptive f-Divergence
【优化】Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization
【Q学习】Non-delusional Q-learning and value-iteration
【几何3D关键点】Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
【优化】Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
【样本高效强化学习】Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion
【未知分类重建】Learning to Reconstruct Shapes from Unseen Classes
【半正定问题】Smoothed analysis of the low-rank approach for smooth semidefinite programs

2.Spotlight

Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces
Global Geometry of Multichannel Sparse Blind Deconvolution on the Sphere
Size-Noise Tradeoffs in Generative Networks
Diffusion Maps for Textual Network Embedding
Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds
Neural Voice Cloning with a Few Samples
Evolved Policy Gradients
Differentially Private Testing of Identity and Closeness of Discrete Distributions
Answerer in Questioner’s Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog
Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning
Local Differential Privacy for Evolving Data
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
Bayesian Model-Agnostic Meta-Learning
Differentially Private k-Means with Constant Multiplicative Error
Learning to Optimize Tensor Programs
Probabilistic Neural Programmed Networks for Scene Generation
A Spectral View of Adversarially Robust Features
A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks
Bias and Generalization in Deep Generative Models: An Empirical Study
Bounded-Loss Private Prediction Markets
Generalizing Tree Probability Estimation via Bayesian Networks
Robustness of conditional GANs to noisy labels
cpSGD: Communication-efficient and differentially-private distributed SGD
Geometry Based Data Generation
BourGAN: Generative Networks with Metric Embeddings
Adversarially Robust Generalization Requires More Data
Point process latent variable models of larval zebrafish behavior
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding
Training Neural Networks Using Features Replay
Towards Robust Detection of Adversarial Examples
Learning Temporal Point Processes via Reinforcement Learning
Step Size Matters in Deep Learning
Neural Architecture Search with Bayesian Optimisation and Optimal Transport
Precision and Recall for Time Series
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
Data-Driven Clustering via Parameterized Lloyd’s Families
Bayesian Nonparametric Spectral Estimation
Hierarchical Graph Representation Learning with Differentiable Pooling
Supervising Unsupervised Learning
A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem
Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images
Revisiting $(ϵ,\gamma ,\tau )$-similarity learning for domain adaptation
Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs
Delta-encoder: an effective sample synthesis method for few-shot object recognition
Leveraged volume sampling for linear regression
End-to-End Differentiable Physics for Learning and Control
Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language
Synthesize Policies for Transfer and Adaptation across Tasks and Environments
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes
Neighbourhood Consensus Networks
Sublinear Time Low-Rank Approximation of Distance Matrices
Acceleration through Optimistic No-Regret Dynamics
Recurrent Transformer Networks for Semantic Correspondence
Minimax Statistical Learning with Wasserstein distances
On Oracle-Efficient PAC RL with Rich Observations
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
Generalization Bounds for Uniformly Stable Algorithms
Constant Regret, Generalized Mixability, and Mirror Descent
Sanity Checks for Saliency Maps
A loss framework for calibrated anomaly detection
Efficient Online Portfolio with Logarithmic Regret
A Probabilistic U-Net for Segmentation of Ambiguous Images
Sharp Bounds for Generalized Uniformity Testing
Solving Large Sequential Games with the Excessive Gap Technique
Virtual Class Enhanced Discriminative Embedding Learning
Convex Elicitation of Continuous Properties
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Dynamic Network Model from Partial Observations
The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
Stochastic Nonparametric Event-Tensor Decomposition
Contextual Stochastic Block Models
Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
On GANs and GMMs
Entropy Rate Estimation for Markov Chains with Large State Space
Meta-Reinforcement Learning of Structured Exploration Strategies
GILBO: One Metric to Measure Them All
Blind Deconvolutional Phase Retrieval via Convex Programming
A Bayesian Approach to Generative Adversarial Imitation Learning
Sparse Covariance Modeling in High Dimensions with Gaussian Processes
Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization
Visual Reinforcement Learning with Imagined Goals
Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features
On the Local Minima of the Empirical Risk
Randomized Prior Functions for Deep Reinforcement Learning
Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior
How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery?
Playing hard exploration games by watching YouTube
Adversarially Robust Optimization with Gaussian Processes
SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator
Reducing Network Agnostophobia
DAGs with NO TEARS: Continuous Optimization for Structure Learning
Natasha 2: Faster Non-Convex Optimization Than SGD
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
Proximal Graphical Event Models
Escaping Saddle Points in Constrained Optimization
Geometrically Coupled Monte Carlo Sampling
Heterogeneous Multi-output Gaussian Process Prediction
On Coresets for Logistic Regression
Scalable Laplacian K-modes
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
Legendre Decomposition for Tensors
Learning with SGD and Random Features
Graphical model inference: Sequential Monte Carlo meets deterministic approximations
Boolean Decision Rules via Column Generation
KONG: Kernels for ordered-neighborhood graphs
Boosting Black Box Variational Inference
Fast greedy algorithms for dictionary selection with generalized sparsity constraints
Quadrature-based features for kernel approximation
Discretely Relaxing Continuous Variables for tractable Variational Inference
Distributed $k$-Clustering for Data with Heavy Noise
Statistical and Computational Trade-Offs in Kernel K-Means
Implicit Reparameterization Gradients
Do Less, Get More: Streaming Submodular Maximization with Subsampling
Why Is My Classifier Discriminatory?
Mirrored Langevin Dynamics
Overlapping Clustering Models, and One (class) SVM to Bind Them All
Human-in-the-Loop Interpretability Prior
Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization
Removing the Feature Correlation Effect of Multiplicative Noise
Link Prediction Based on Graph Neural Networks
Identification and Estimation of Causal Effects from Dependent Data
Connectionist Temporal Classification with Maximum Entropy Regularization
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
Causal Inference via Kernel Deviance Measures
Entropy and mutual information in models of deep neural networks
Automatic differentiation in ML: Where we are and where we should be going
Removing Hidden Confounding by Experimental Grounding
The committee machine: Computational to statistical gaps in learning a two-layers neural network
Robust Subspace Approximation in a Stream
Hyperbolic Neural Networks
A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization
Efficient nonmyopic batch active search
Norm matters: efficient and accurate normalization schemes in deep networks
Stochastic Chebyshev Gradient Descent for Spectral Optimization
Interactive Structure Learning with Structural Query-by-Committee
Constructing Fast Network through Deconstruction of Convolution
LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning
Contour location via entropy reduction leveraging multiple information sources
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames
Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes
Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction
Direct Runge-Kutta Discretization Achieves Acceleration
Learning convex bounds for linear quadratic control policy synthesis
Learning Loop Invariants for Program Verification
Limited Memory Kelley’s Method Converges for Composite Convex and Submodular Objectives
Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning
DeepProbLog: Neural Probabilistic Logic Programming
(Probably) Concave Graph Matching
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
Learning to Infer Graphics Programs from Hand-Drawn Images
Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
Bilevel learning of the Group Lasso structure
Improving Neural Program Synthesis with Inferred Execution Traces
Wasserstein Distributionally Robust Kalman Filtering
Binary Classification from Positive-Confidence Data
ResNet with one-neuron hidden layers is a Universal Approximator
Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenters
Fully Understanding The Hashing Trick
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation
Robust Hypothesis Testing Using Wasserstein Uncertainty Sets
Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
Convergence of Cubic Regularization for Nonconvex Optimization under KL Property

pic from mcgill.ca, icon from easyicon.com

---

ref：
spot： 'https://nips.cc/Conferences/2018/Schedule?type=Spotlight
oral： 'https://nips.cc/Conferences/2018/Schedule?type=Oral