ICML 2018 paper(oral)

参考链接

• icml 2018 oral

Paperlist

Optimal Tuning for Divide-and-conquer Kernel Ridge Regression with Massive Data
Predict and Constrain: Modeling Cardinality in Deep Structured Prediction
Transfer Learning via Learning to Transfer
Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs
Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
Crowdsourcing with Arbitrary Adversaries
DiCE: The Infinitely Differentiable Monte Carlo Estimator
Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
SparseMAP: Differentiable Sparse Structured Inference
Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model
Do Outliers Ruin Collaboration?
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
Quickshift++: Provably Good Initializations for Sample-Based Mean Shift
Distributed Nonparametric Regression under Communication Constraints
Nonoverlap-Promoting Variable Selection
Learning to search with MCTSnets
Learning with Abandonment
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
Hierarchical Clustering with Structural Constraints
Differentiable plasticity: training plastic neural networks with backpropagation
Lipschitz Continuity in Model-based Reinforcement Learning
Conditional Noise-Contrastive Estimation of Unnormalised Models
Tree Edit Distance Learning via Adaptive Symbol Embeddings
MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration
Coded Sparse Matrix Multiplication
Deep One-Class Classification
Bilevel Programming for Hyperparameter Optimization and Meta-Learning
Black Box FDR
TACO: Learning Task Decomposition via Temporal Alignment for Control
Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication
Implicit Quantile Networks for Distributional Reinforcement Learning
Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations
K-means clustering using random matrix sparsification
Variational Network Inference: Strong and Stable with Concrete Support
Efficient and Consistent Adversarial Bipartite Matching
Network Global Testing by Counting Graphlets
More Robust Doubly Robust Off-policy Evaluation
Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach
Graph Networks as Learnable Physics Engines for Inference and Control
Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines
Deep Density Destructors
CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions
Learning to Speed Up Structured Output Prediction
Clustering Semi-Random Mixtures of Gaussians
Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back
Markov Modulated Gaussian Cox Processes for Semi-Stationary Intensity Modeling of Events Data
Asynchronous Decentralized Parallel Stochastic Gradient Descent
Coordinated Exploration in Concurrent Reinforcement Learning
Stagewise Safe Bayesian Optimization with Gaussian Processes
RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski $p$-Norms
Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design
Improving Optimization in Models With Continuous Symmetry Breaking
Data-Dependent Stability of Stochastic Gradient Descent
WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models
Bayesian Quadrature for Multiple Related Integrals
Structured Evolution with Compact Architectures for Scalable Policy Optimization
Stability and Generalization of Learning Algorithms that Converge to Global Optima
Semi-Supervised Learning via Compact Latent Space Clustering
BOCK : Bayesian Optimization with Cylindrical Kernels
Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization
signSGD: Compressed Optimisation for Non-Convex Problems
Nearly Optimal Robust Subspace Tracking
Subspace Embedding and Linear Regression with Orlicz Norm
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks
Spotlight: Optimizing Device Placement for Training Deep Neural Networks
Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization
Gated Path Planning Networks
Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces
Safe Element Screening for Submodular Function Minimization
Katyusha X: Simple Momentum Method for Stochastic Sum-of-Nonconvex Optimization
Conditional Neural Processes
Learning Steady-States of Iterative Algorithms over Graphs
An Estimation and Analysis Framework for the Rasch Model
BOHB: Robust and Efficient Hyperparameter Optimization at Scale
Differentiable Compositional Kernel Learning for Gaussian Processes
Online Convolutional Sparse Coding with Sample-Dependent Dictionary
Streaming Principal Component Analysis in Noisy Setting
$D^2$: Decentralized Training over Decentralized Data
Dropout Training, Data-dependent Regularization, and Generalization Bounds
Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression
A Semantic Loss Function for Deep Learning with Symbolic Knowledge
Bayesian Optimization of Combinatorial Structures
End-to-end Active Object Tracking via Reinforcement Learning
Best Arm Identification in Linear Bandits with Linear Dimension Dependency
Anonymous Walk Embeddings
Non-linear motor control by local learning in spiking neural networks
Structured Control Nets for Deep Reinforcement Learning
An Alternative View: When Does SGD Escape Local Minima?
Linear Spectral Estimators and an Application to Phase Retrieval
Deep Predictive Coding Network for Object Recognition
Generative Temporal Models with Spatial Memory for Partially Observed Environments
Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches
Variational Inference and Model Selection with Generalized Evidence Bounds
The Limits of Maxing, Ranking, and Preference Learning
Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization
Disentangling by Factorising
Selecting Representative Examples for Program Synthesis
Latent Space Policies for Hierarchical Reinforcement Learning
Learning a Mixture of Two Multinomial Logits
Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization
Fixing a Broken ELBO
Escaping Saddles with Stochastic Gradients
The Generalization Error of Dictionary Learning with Moreau Envelopes
Gradually Updated Neural Networks for Large-Scale Image Recognition
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
Discovering Interpretable Representations for Both Deep Generative and Discriminative Models
Neural Inverse Rendering for General Reflectance Photometric Stereo
On Learning Sparsely Used Dictionaries from Incomplete Samples
Hierarchical Long-term Video Prediction without Supervision
The Weighted Kendall and High-order Kernels for Permutations
Learning Independent Causal Mechanisms
On the Relationship between Data Efficiency and Error for Uncertainty Sampling
Parameterized Algorithms for the Matrix Completion Problem
Signal and  Noise Statistics Oblivious Orthogonal Matching Pursuit
Stochastic Variance-Reduced Cubic Regularized Newton Method
The Well-Tempered Lasso
Tighter Variational Bounds are Not Necessarily Better
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
One-Shot Segmentation in Clutter
Differentially Private Identity and Equivalence Testing of Discrete Distributions
Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
An Inference-Based Policy Gradient Method for Learning Options
Non-convex Conditional Gradient Sliding
Continuous-Time Flows for Efficient Inference and Density Estimation
Active Testing: An Efficient and Robust Framework for Estimating Accuracy
Testing Sparsity over Known and Unknown Bases
Model-Level Dual Learning
Differentially Private Matrix Completion Revisited
Programmatically Interpretable Reinforcement Learning
Semi-Implicit Variational Inference
Adafactor: Adaptive Learning Rates with Sublinear Memory Cost
Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs
Stochastic Training of Graph Convolutional Networks with Variance Reduction
Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?
Which Training Methods for GANs do actually Converge?
Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
Chi-square Generative Adversarial Network
Orthogonal Recurrent Neural Networks with Scaled Cayley Transform
Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees
Feedback-Based Tree Search for Reinforcement Learning
Learning by Playing - Solving Sparse Reward Tasks from Scratch
Efficient Gradient-Free Variational Inference using Policy Search
Representation Learning on Graphs with Jumping Knowledge Networks
Mitigating Bias in Adaptive Data Gathering via Differential Privacy
Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams
The Dynamics of Learning: A Random Matrix Approach
ADMM and Accelerated ADMM as Continuous Dynamical Systems
Kronecker Recurrent Units
Local Private Hypothesis Testing: Chi-Square Tests
Locally Private Hypothesis Testing
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm
Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling
Learning Diffusion using Hyperparameters
Automatic Goal Generation for Reinforcement Learning Agents
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
Fast Parametric Learning with Activation Memorization
A Spectral Approach to Gradient Estimation for Implicit Distributions
Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints
Learning Implicit Generative Models with the Method of Learned Moments
Data Summarization at Scale: A Two-Stage Submodular Approach
Dynamic Evaluation of Neural Sequence Models
Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control
Quasi-Monte Carlo Variational Inference
Canonical Tensor Decomposition for Knowledge Base Completion
A Classification-Based Study of Covariate Shift in GAN Distributions
Learning the Reward Function for a Misspecified Model
INSPECTRE: Privately Estimating the Unseen
An Efficient Semismooth Newton based Algorithm for Convex Clustering
Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global
The Power of Interpolation:  Understanding the Effectiveness of SGD in Modern Over-parametrized Learning
Dependent Relational Gamma Process Models for Longitudinal Networks
Learning to Optimize Combinatorial Functions
Yes, but Did It Work?: Evaluating Variational Inference
Machine Theory of Mind
Delayed Impact of Fair Machine Learning
Differentiable Abstract Interpretation for Provably Robust Neural Networks
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning
Decoupled Parallel Backpropagation with Convergence Guarantee
Essentially No Barriers in Neural Network Energy Landscape
Comparing Dynamics: Deep Neural Networks versus Glassy Systems
Path Consistency Learning in Tsallis Entropy Regularized MDPs
Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope
Augment and Reduce: Stochastic Inference for Large Categorical Distributions
Fairness Without Demographics in Repeated Loss Minimization
Fast Variance Reduction Method with Stochastic Batch Size
Efficient Neural Architecture Search via Parameters Sharing
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy
NetGAN: Generating Graphs via Random Walks
Binary Partitions with Approximate  Minimum Impurity
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
Not All Samples Are Created Equal: Deep Learning with Importance Sampling
Synthesizing Robust Adversarial Examples
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
Been There, Done That: Meta-Learning with Episodic Recall
Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
Learning Deep ResNet Blocks Sequentially using Boosting Theory
Nonconvex Optimization for Regression with Fairness Constraints
Black-Box Variational Inference for Stochastic Differential Equations
Partial Optimality and Fast Lower Bounds for Weighted Correlation Clustering
Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems
Continual Reinforcement Learning with Complex Synapses
Bounds on the Approximation Power of Feedforward Neural Networks
Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator
Neural Relational Inference for Interacting Systems
Inference Suboptimality in Variational Autoencoders
Fair and Diverse DPP-Based Data Summarization
An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
Spline Filters For End-to-End Deep Learning
A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time
Learning Memory Access Patterns
Learning unknown ODE models with Gaussian processes
Convergent Tree Backup and Retrace with Function Approximation
Probabilistic Boolean Tensor Decomposition
Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks
Multicalibration: Calibration for the (Computationally-Identifiable) Masses
Learning Policy Representations in Multiagent Systems
Geometry Score: A Method For Comparing Generative Adversarial Networks
Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization
Compressing Neural Networks using the Variational Information Bottelneck
Residual Unfairness in Fair Machine Learning from Prejudiced Data
SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
Geodesic Convolutional Shape Optimization
Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems
Optimizing the Latent Space of Generative Networks
Differentiable Dynamic Programming for Structured Prediction and Attention
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery
Constraining the Dynamics of Deep Probabilistic Models
Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion
Adversarial Learning with Local Coordinate Coding
Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
Learning to Act in Decentralized Partially Observable MDPs
Scalable Bilinear Pi Learning Using State and Action Features
Probabilistic Recurrent State-Space Models
Kernelized Synaptic Weight Matrices
DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding
Learning Representations and Generative Models for 3D Point Clouds
Structured Output Learning with Abstention: Application to Accurate Opinion Prediction
Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms
Learning Binary Latent Variable Models: A Tensor Eigenpair Approach
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning
Modeling Others using Oneself in Multi-Agent Reinforcement Learning
Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization
Stochastic Variance-Reduced Policy Gradient
Theoretical Analysis of Image-to-Image Translation with Adversarial Learning
Deep Models of Interactions Across Sets
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
End-to-End Learning for the Deep Multivariate Probit Model
Structured Variationally Auto-encoded Optimization
Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?
Adversarial Regression with Multiple Learners
Investigating Human Priors for Playing Video Games
Fast Information-theoretic Bayesian Optimisation
Composite Functional Gradient Learning of Generative  Adversarial Models
Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap
Focused Hierarchical RNNs for Conditional Sequence Processing
Accelerated Spectral Ranking
Learning One Convolutional Layer with Overlapping Patches
Inductive Two-Layer Modeling with Parametric Bregman Transfer
Shampoo: Preconditioned Stochastic Tensor Optimization
Improved large-scale graph learning through ridge spectral sparsification
Optimization, fast and slow: optimally switching between local and Bayesian optimization
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima
Parallel and Streaming Algorithms for K-Core Decomposition
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
Composite Marginal Likelihood Methods for Random Utility Models
Characterizing Implicit Bias in Terms of Optimization Geometry
Does Distributionally Robust Supervised Learning Give Robust Classifiers?
Tempered Adversarial Networks
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Prediction Rule Reshaping
Ranking Distributions based on Noisy Sorting
A Distributed Second-Order Algorithm You Can Trust
Stochastic Variance-Reduced Hamilton Monte Carlo Methods
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms
Improved Training of Generative Adversarial Networks Using Representative Features
Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design
The Multilinear Structure of ReLU Networks
A Robust Approach to Sequential Information Theoretic Planning
A Two-Step Computation of the Exact GAN Wasserstein Distance
Time Limits in Reinforcement Learning
Fast Approximate Spectral Clustering for Dynamic Networks
Learning long term dependencies via Fourier recurrent units
A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning
SQL-Rank: A Listwise Approach to Collaborative Ranking
Finding Influential Training Samples for Gradient Boosted Decision Trees
Understanding the Loss Surface of Neural Networks for Binary Classification
Extreme Learning to Rank via Low Rank Assumption
Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order
Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms
Is Generator Conditioning Causally Related to GAN Performance?
Visualizing and Understanding Atari Agents
Noise2Noise: Learning Image Restoration without Clean Data
Training Neural Machines with Trace-Based Supervision
Gradient Coding from Cyclic MDS Codes and Expander Graphs
Tight Regret Bounds for Bayesian Optimization in One Dimension
Feasible Arm Identification
The Mirage of Action-Dependent Baselines in Reinforcement Learning
Dimensionality-Driven Learning with Noisy Labels
Black-box Adversarial Attacks with Limited Queries and Information
Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices
To Understand Deep Learning We Need to Understand Kernel Learning
Neural Dynamic Programming for Musical Self Similarity
Robust and Scalable Models of Microbiome Dynamics
Alternating Randomized Block Coordinate Descent
Tropical Geometry of Deep Neural Networks
Randomized Block Cubic Newton Method
Loss Decomposition for Fast Learning in Large Output Spaces
A Spline Theory of Deep Learning
Stein Variational Message Passing for Continuous Graphical Models
Smoothed Action Value Functions for Learning Gaussian Policies
Bandits with Delayed, Aggregated Anonymous Feedback
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
Kernel Recursive ABC: Point Estimation with Intractable Likelihood
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models
Ultra Large-Scale Feature Selection using Count-Sketches
Learning to Reweight Examples for Robust Deep Learning
Fast Decoding in Sequence Models Using Discrete Latent Variables
Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions
Accelerating Greedy Coordinate Descent Methods
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions
PixelSNAIL: An Improved Autoregressive Generative Model
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits
Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion
Differentially Private Database Release via Kernel Mean Embeddings
Adversarial Attack on Graph Structured Data
Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
Image Transformer
Improving Regression Performance with Distributional Losses
Learning in Reproducing Kernel Kreı̆n Spaces
On Acceleration with Noise-Corrupted Gradients
Addressing Function Approximation Error in Actor-Critic Methods
Bucket Renormalization for Approximate Inference
GAIN: Missing Data Imputation using Generative Adversarial Nets
Stronger Generalization Bounds for Deep Nets via a Compression Approach
Semi-Supervised Learning on Data Streams via Temporal Label Propagation
Thompson Sampling for Combinatorial Semi-Bandits
Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings
Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods
Reviving and Improving Recurrent Back-Propagation
Using Inherent Structures to design Lean 2-layer RBMs
Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity
Approximate message passing for amplitude based optimization
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
Configurable Markov Decision Processes
Variational Bayesian dropout: pitfalls and fixes
The Mechanics of n-Player Differentiable Games
Beyond the One-Step Greedy Approach in Reinforcement Learning
Deep Asymmetric Multi-task Feature Learning
Approximation Guarantees for Adaptive Sampling
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks
K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning
Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Accurate Uncertainties for Deep Learning Using Calibrated Regression
Practical Contextual Bandits with Regression Oracles
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
Invariance of Weight Distributions in Rectified MLPs
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
Greed is Still Good: Maximizing Monotone Submodular+Supermodular (BP) Functions
First Order Generative Adversarial Networks
Functional Gradient Boosting based on Residual Network Perception
Towards Fast Computation of Certified Robustness for ReLU Networks
prDeep: Robust Phase Retrieval with a Flexible Deep Network
Policy and Value Transfer in Lifelong Reinforcement Learning
Learning Dynamics of Linear Denoising Autoencoders
Constrained Interacting Submodular Groupings
Scalable approximate Bayesian inference for particle tracking data
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples
Fitting New Speakers Based on a Short Untranscribed Sample
Fast Stochastic AUC Maximization with $O(1/n)$-Convergence Rate
Stochastic Proximal Algorithms for AUC Maximization
Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice
LaVAN: Localized and Visible Adversarial Noise
Importance Weighted Transfer of Samples in Reinforcement Learning
Binary Classification with Karmic, Threshold-Quasi-Concave Metrics
Towards Binary-Valued Gates for Robust LSTM Training
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
Accelerating Natural Gradient with Higher-Order Invariance
High Performance Zero-Memory Overhead Direct Convolutions
Understanding Generalization and Optimization Performance of Deep CNNs
Representation Tradeoffs for Hyperbolic Embeddings
Stochastic Wasserstein Barycenters
An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games
Composable Planning with Attributes
Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation
Synthesizing Programs for Images using Reinforced Adversarial Learning
Neural Autoregressive Flows
SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate
ContextNet: Deep learning for Star Galaxy Classification
Deep Variational Reinforcement Learning for POMDPs
Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under $\ell_p$ Distances
Distilling the Posterior in Bayesian Neural Networks
MAGAN: Aligning Biological Manifolds
Fast Bellman Updates for Robust MDPs
Measuring abstract reasoning in neural networks
Autoregressive Convolutional Neural Networks for Asynchronous Time Series
Learning Compact Neural Networks with Regularization
Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer
Open Category Detection with PAC Guarantees
Hierarchical Multi-Label Classification Networks
Riemannian Stochastic Recursive Gradient Algorithm with Retraction and Vector Transport and Its Convergence Analysis
Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
Max-Mahalanobis Linear Discriminant Analysis Networks
Decoupling Gradient-Like Learning Rules from Representations
Unbiased Objective Estimation in Predictive Optimization
Self-Bounded Prediction Suffix Tree via Approximate String Matching
Adversarial Time-to-Event Modeling
Noisy Natural Gradient as Variational Inference
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
Local Density Estimation in High Dimensions
Low-Rank Riemannian Optimization on Positive Semidefinite Stochastic Matrices with Applications to Graph Clustering
Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection
Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy
Recurrent Predictive State Policy Networks
Nonparametric variable importance using an augmented neural network with multi-task learning
Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning
Explicit Inductive Bias for Transfer Learning with Convolutional Networks
Learning Localized Spatio-Temporal Models From Streaming Data
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
Improving Sign Random Projections With Additional Information
Regret Minimization for Partially Observable Deep Reinforcement Learning
Towards Black-box Iterative Machine Teaching
Knowledge Transfer with Jacobian Matching
Graphical Nonconvex Optimization via an Adaptive Convex Relaxation
Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training
RLlib: Abstractions for Distributed Reinforcement Learning
A Reductions Approach to Fair Classification
Mixed batches and symmetric discriminators for GAN training
Dynamic Regret of Strongly Adaptive Methods
Out-of-sample extension of graph adjacency spectral embedding
Learning Registered Point Processes from Idiosyncratic Observations
Convergence guarantees for a class of non-convex and   non-smooth optimization problems
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
Learning in Integer Latent Variable Models with Nested Automatic Differentiation
Solving Partial Assignment Problems using Random Clique Complexes
A Progressive Batching L-BFGS Method for Machine Learning
Online Learning with Abstention
Deep Bayesian Nonparametric Tracking
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Bayesian Model Selection for Change Point Detection and Clustering
Sound Abstraction and Decomposition of Probabilistic Programs
Probably Approximately Metric-Fair Learning
Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction
Learning equations for extrapolation and control
Mutual Information Neural Estimation
Parallel Bayesian Network Structure Learning
An Iterative, Sketching-based Framework for Ridge Regression
Multi-Fidelity Black-Box Optimization with Hierarchical Partitions
PDE-Net: Learning PDEs from Data
Adversarially Regularized Autoencoders
Video Prediction with Appearance and Motion Conditions
Mix & Match - Agent Curricula for Reinforcement Learning
Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for  Nonconvex Distributed Optimization Over Networks
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits
The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference
Neural Program Synthesis from Diverse Demonstration Videos
Transformation Autoregressive Networks
Provable Variable Selection for Streaming Features
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Temporal Poisson Square Root Graphical Models
Learning Low-Dimensional Temporal Representations
Firing Bandits: Optimizing Crowdfunding
Learning to Explore via Meta-Policy Gradient
Blind Justice: Fairness with Encrypted Sensitive Attributes
Weightless: Lossy weight encoding for deep neural network compression
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
Estimation of Markov Chain via Rank-constrained Likelihood
Hierarchical Imitation and Reinforcement Learning
Competitive Caching with Machine Learned Advice
Theoretical Analysis of Sparse Subspace Clustering with Missing Entries
Scalable Gaussian Processes with Grid-Structured Eigenfunctions (GP-GRIEF)
Online Linear Quadratic Control
Junction Tree Variational Autoencoder for Molecular Graph Generation
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
Learning Adversarially Fair and Transferable Representations
Efficient Neural Audio Synthesis
A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming