ICML 2017 Events with Videos

Invited Talks

• Causal Learning
• Genomics, Big Data, and Machine Learning: Understanding the Human Wiring Diagram and Driving the Healthcare Revolution
• Towards Reinforcement Learning in the Real World
• How AI Designers will Dictate Our Civic Future

Talks

• Multi-objective Bandits: Optimizing the Generalized Gini Index
• Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis
• Robust Adversarial Reinforcement Learning
• Enumerating Distinct Decision Trees
• The loss surface of deep and wide neural networks
• Robust Probabilistic Modeling with Bayesian Data Reweighting
• PixelCNN Models with Auxiliary Variables for Natural Image Modeling
• Tight Bounds for Approximate Carathéodory and Beyond
• Online Learning with Local Permutations and Delayed Feedback
• SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling
• Minimax Regret Bounds for Reinforcement Learning
• Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation
• Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks
• Post-Inference Prior Swapping
• Understanding Synthetic Gradients and Decoupled Neural Interfaces
• Parallel Multiscale Autoregressive Density Estimation
• Oracle Complexity of Second-Order Methods for Finite-Sum Problems
• Model-Independent Online Learning for Influence Maximization
• Latent Feature Lasso
• Fairness in Reinforcement Learning
• Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things
• Sharp Minima Can Generalize For Deep Nets
• Evaluating Bayesian Models with Posterior Dispersion Indices
• meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting
• Global optimization of Lipschitz functions
• Online Learning to Rank in Stochastic Click Models
• Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability
• Boosted Fitted Q-Iteration
• Multi-Class Optimal Margin Distribution Machine
• Geometry of Neural Network Loss Surfaces via Random Matrix Theory
• Automatic Discovery of the Statistical Types of Variables in a Dataset
• Learning Important Features Through Propagating Activation Differences
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions
• The Sample Complexity of Online One-Class Collaborative Filtering
• Why is Posterior Sampling Better than Optimism for Reinforcement Learning?
• Kernelized Support Tensor Machines
• The Shattered Gradients Problem: If resnets are the answer, then what is the question?
• Bayesian Models of Data Streams with Hierarchical Power Priors
• Evaluating the Variance of Likelihood-Ratio Gradient Estimators
• Learning Texture Manifolds with the Periodic Spatial GAN
• Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence
• Efficient Regret Minimization in Non-Convex Games
• Coresets for Vector Summarization with Applications to Network Graphs
• Constrained Policy Optimization
• Dual Supervised Learning
• Recovery Guarantees for One-hidden-layer Neural Networks
• Ordinal Graphical Models: A Tale of Two Approaches
• Equivariance Through Parameter-Sharing
• Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization
• Identify the Nash Equilibrium in Static Games with Random Payoffs
• Partitioned Tensor Factorizations for Learning Mixed Membership Models
• Reinforcement Learning with Deep Energy-Based Policies
• Learning Infinite Layer Networks without the Kernel Trick
• Failures of Gradient-Based Deep Learning
• Scalable Bayesian Rule Lists
• Warped Convolutions: Efficient Invariance to Spatial Transformations
• McGan: Mean and Covariance Feature Matching GAN
• Breaking Locality Accelerates Block Gauss-Seidel
• Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU
• On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations
• Prediction and Control with Temporal Segment Models
• Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees
• Analytical Guarantees on Numerical Precision of Deep Neural Networks
• Learning Determinantal Point Processes with Moments and Cycles
• Graph-based Isometry Invariant Representation Learning
• Conditional Image Synthesis with Auxiliary Classifier GANs
• Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification
• On Kernelized Multi-armed Bandits
• Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates
• An Alternative Softmax Operator for Reinforcement Learning
• Logarithmic Time One-Against-Some
• Follow the Moving Leader in Deep Learning
• Deep Bayesian Active Learning with Image Data
• Deriving Neural Architectures from Sequence and Graph Kernels
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares
• Second-Order Kernel Online Convex Optimization with Adaptive Sketching
• Frame-based Data Factorizations
• Fake News Mitigation via Point Process Based Intervention
• Understanding Black-box Predictions via Influence Functions
• Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
• Bayesian Boolean Matrix Factorisation
• Wasserstein Generative Adversarial Networks
• Connected Subgraph Detection with Mirror Descent on SDPs
• Dueling Bandits with Weak Regret
• Nearly Optimal Robust Matrix Completion
• Curiosity-driven Exploration by Self-supervised Prediction
• Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method
• Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
• Learning the Structure of Generative Models without Labeled Data
• Deep Transfer Learning with Joint Adaptation Networks
• Learning Hierarchical Features from Deep Generative Models
• Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks
• On Context-Dependent Clustering of Bandits
• Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations
• Interactive Learning from Policy-Dependent Human Feedback
• Self-Paced Co-training
• Convexified Convolutional Neural Networks
• Learning to Discover Sparse Graphical Models
• Meta Networks
• Bottleneck Conditional Density Estimation
• Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
• Provably Optimal Algorithms for Generalized Linear Contextual Bandits
• No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis
• End-to-End Differentiable Adversarial Imitation Learning
• Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data
• On the Expressive Power of Deep Neural Networks
• Local-to-Global Bayesian Network Structure Learning
• SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization
• Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo
• Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization
• Safety-Aware Algorithms for Adversarial Contextual Bandit
• Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery
• Learning in POMDPs with Monte Carlo Tree Search
• Iterative Machine Teaching
• Depth-Width Tradeoffs in Approximating Natural Functions With Neural Networks
• Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Zero-Inflated Exponential Family Embeddings
• A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates
• Adaptive Multiple-Arm Identification
• Tensor Decomposition with Smoothness
• DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
• Automated Curriculum Learning for Neural Networks
• On Relaxing Determinism in Arithmetic Circuits
• AdaNet: Adaptive Structural Learning of Artificial Neural Networks
• Convex Phase Retrieval without Lifting via PhaseMax
• Efficient Online Bandit Multiclass Learning with O(sqrt{T}) Regret
• Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use
• Unifying task specification in reinforcement learning
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Efficient Nonmyopic Active Search
• An Infinite Hidden Markov Model With Similarity-Biased Transitions
• Learning to Learn without Gradient Descent by Gradient Descent
• Attentive Recurrent Comparators
• A Semismooth Newton Method for Fast, Generic Convex Programming
• Active Learning for Accurate Estimation of Linear Models
• Tensor Decomposition via Simultaneous Power Iteration
• A Distributional Perspective on Reinforcement Learning
• Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression
• Leveraging Union of Subspace Structure to Improve Constrained Clustering
• Batched High-dimensional Bayesian Optimization via Structural Kernel Learning
• Learned Optimizers that Scale and Generalize
• State-Frequency Memory Recurrent Neural Networks
• Approximate Newton Methods and Their Local Convergence
• Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP
• A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery
• Hierarchy Through Composition with Multitask LMDPs
• Multi-task Learning with Labeled and Unlabeled Tasks
• Active Heteroscedastic Regression
• From Patches to Images: A Nonparametric Generative Model
• Learning Gradient Descent: Better Generalization and Longer Horizons
• Delta Networks for Optimized Recurrent Network Computation
• Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values
• Emulating the Expert: Inverse Optimization through Online Learning
• An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation
• A Laplacian Framework for Option Discovery in Reinforcement Learning
• Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
• Active Learning for Cost-Sensitive Classification
• Fast Bayesian Intensity Estimation for the Permanental Process
• Learning Algorithms for Active Learning
• Recurrent Highway Networks
• Practical Gauss-Newton Optimisation for Deep Learning
• Variants of RMSProp and Adagrad with Logarithmic Regret Bounds
• Algorithms for $\ell_p$ Low-Rank Approximation
• Modular Multitask Reinforcement Learning with Policy Sketches
• Risk Bounds for Transferring Representations With and Without Fine-Tuning
• Diameter-Based Active Learning
• A Birth-Death Process for Feature Allocation
• Tensor Balancing on Statistical Manifold
• Test of Time Award
• Leveraging Node Attributes for Incomplete Relational Data
• How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?
• Data-Efficient Policy Evaluation Through Behavior Policy Search
• Distributed and Provably Good Seedings for k-Means in Constant Rounds
• Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging
• Exact MAP Inference by Avoiding Fractional Vertices
• Relative Fisher Information and Natural Gradient for Learning Large Modular Models
• Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections
• Lazifying Conditional Gradient Algorithms
• Bayesian inference on random simple graphs with power law degree distributions
• Faster Principal Component Regression and Stable Matrix Chebyshev Approximation
• Stochastic Variance Reduction Methods for Policy Evaluation
• Consistent k-Clustering
• Estimating the unseen from multiple populations
• Exact Inference for Integer Latent-Variable Models
• Learning Deep Architectures via Generalized Whitened Neural Networks
• On orthogonality and learning RNNs with long term dependencies
• Conditional Accelerated Lazy Stochastic Gradient Descent
• Analogical Inference for Multi-relational Embeddings
• Spectral Learning from a Single Trajectory under Finite-State Policies
• Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• Meritocratic Fairness for Cross-Population Selection
• Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms
• Continual Learning Through Synaptic Intelligence
• Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
• SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
• Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
• Capacity Releasing Diffusion for Speed and Locality.
• Consistent On-Line Off-Policy Evaluation
• Hyperplane Clustering Via Dual Principal Component Pursuit
• Neural networks and rational functions
• Variational Inference for Sparse and Undirected Models
• Adaptive Neural Networks for Efficient Inference
• The Statistical Recurrent Unit
• Approximate Steepest Coordinate Descent
• Deep Generative Models for Relational Data with Side Information
• Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition
• Contextual Decision Processes with low Bellman rank are PAC-Learnable
• Multilevel Clustering via Wasserstein Means
• Tensor Belief Propagation
• Combined Group and Exclusive Sparsity for Deep Neural Networks
• Input Switched Affine Networks: An RNN Architecture Designed for Interpretability
• StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent
• On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit
• A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical Proficiency
• Co-clustering through Optimal Transport
• Uniform Deviation Bounds for k-Means Clustering
• Faster Greedy MAP Inference for Determinantal Point Processes
• Input Convex Neural Networks
• Online and Linear-Time Attention by Enforcing Monotonic Alignments
• Stochastic modified equations and adaptive stochastic gradient algorithms
• Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening
• Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization
• Gradient Boosted Decision Trees for High Dimensional Sparse Output
• Multiple Clustering Views from Multiple Uncertain Experts
• Uniform Convergence Rates for Kernel Density Estimation
• Zonotope hit-and-run for efficient sampling from projection DPPs
• OptNet: Differentiable Optimization as a Layer in Neural Networks
• Sequence Tutor: Conservative fine-tuning of sequence generation models with KL-control
• Dissipativity Theory for Nesterov's Accelerated Method
• Just Sort It! A Simple and Effective Approach to Active Preference Learning
• On The Projection Operator to A Three-view Cardinality Constrained Set
• Globally Induced Forest: A Prepruning Compression Scheme
• Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery
• Density Level Set Estimation on Manifolds with DBSCAN
• Parseval Networks: Improving Robustness to Adversarial Examples
• Deep Voice: Real-time Neural Text-to-Speech
• An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis
• Maximum Selection and Ranking under Noisy Comparisons
• Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity
• Forest-type Regression with General Losses and Robust Forest
• Clustering High Dimensional Dynamic Data Streams
• Algorithmic Stability and Hypothesis Complexity
• On the Sampling Problem for Kernel Quadrature
• Regularising Non-linear Models Using Feature Side-information
• DeepBach: a Steerable Model for Bach Chorales Generation
• Forward and Reverse Gradient-Based Hyperparameter Optimization
• Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons
• Compressed Sensing using Generative Models
• Confident Multiple Choice Learning
• Consistency Analysis for Binary Classification Revisited
• Measuring Sample Quality with Kernels
• Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
• Adaptive Sampling Probabilities for Non-Smooth Optimization
• Learning to Align the Source Code to the Compiled Object Code
• Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction
• Regret Minimization in Behaviorally-Constrained Zero-Sum Games
• Fast k-Nearest Neighbour Search via Prioritized DCI
• Distributed Mean Estimation with Limited Communication
• Variational Boosting: Iteratively Refining Posterior Approximations
• A Closer Look at Memorization in Deep Networks
• Learning to Generate Long-term Future via Hierarchical Prediction
• Sub-sampled Cubic Regularization for Non-convex Optimization
• RobustFill: Neural Program Learning under Noisy I/O
• Efficient Distributed Learning with Sparsity
• Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning
• Deep Spectral Clustering Learning
• Nonparanormal Information Estimation
• Lost Relatives of the Gumbel Trick
• Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
• Sequence to Better Sequence: Continuous Revision of Combinatorial Structures
• Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter
• Programming with a Differentiable Forth Interpreter
• Innovation Pursuit: A New Approach to the Subspace Clustering Problem
• Strongly-Typed Agents are Guaranteed to Interact Safely
• Joint Dimensionality Reduction and Metric Learning: A Geometric Take
• A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions
• Learning to Aggregate Ordinal Labels by Maximizing Separating Width
• Visualizing and Understanding Multilayer Perceptron Models: A Case Study in Speech Processing
• Tensor-Train Recurrent Neural Networks for Video Classification
• “Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions
• Differentiable Programs with Neural Libraries
• Selective Inference for Sparse High-Order Interaction Models
• Coordinated Multi-Agent Imitation Learning
• ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices
• Gradient Coding: Avoiding Stragglers in Distributed Learning
• Uncorrelation and Evenness: a New Diversity-Promoting Regularizer
• Axiomatic Attribution for Deep Networks
• Sequence Modeling via Segmentations
• Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization
• Developing Bug-Free Machine Learning Systems With Formal Mathematics
• Dictionary Learning Based on Sparse Distribution Tomography
• Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
• Learning Discrete Representations via Information Maximizing Self-Augmented Training
• Learning Latent Space Models with Angular Constraints
• On Calibration of Modern Neural Networks
• Latent LSTM Allocation: Joint clustering and non-linear dynamic modeling of sequence data
• How to Escape Saddle Points Efficiently
• Preferential Bayesian Optmization
• Being Robust (in High Dimensions) Can Be Practical
• Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution
• When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience Applications
• Differentially Private Ordinary Least Squares
• Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for MCMC
• Device Placement Optimization with Reinforcement Learning
• Dynamic Word Embeddings
• Asynchronous Stochastic Gradient Descent with Delay Compensation
• Max-value Entropy Search for Efficient Bayesian Optimization
• Multilabel Classification with Group Testing and Codes
• Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning
• Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis
• Priv’IT: Private and Sample Efficient Identity Testing
• Stochastic Bouncy Particle Sampler
• Deep Tensor Convolution on Multicores
• Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling
• Adaptive Consensus ADMM for Distributed Optimization
• Bayesian Optimization with Tree-structured Dependencies
• High-Dimensional Structured Quantile Regression
• Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control
• Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier
• Differentially Private Submodular Maximization: Data Summarization in Disguise
• Canopy --- Fast Sampling with Cover Trees
• MEC: Memory-efficient Convolution for Deep Neural Network
• Coupling Distributed and Symbolic Execution for Natural Language Queries
• Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks
• Multi-fidelity Bayesian Optimisation with Continuous Approximations
• High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function Estimation
• Learning Stable Stochastic Nonlinear Dynamical Systems
• iSurvive: An Interpretable, Event-time Prediction Model for mHealth
• Differentially Private Learning of Graphical Models using CGMs
• A Simulated Annealing Based Inexact Oracle for Wasserstein Loss Minimization
• Beyond Filters: Compact Feature Map for Portable Deep Model
• Image-to-Markup Generation with Coarse-to-Fine Attention
• Projection-free Distributed Online Learning in Networks
• Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space
• Robust Structured Estimation with Single-Index Models
• Local Bayesian Optimization of Motor Skills
• Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture
• Minimizing Trust Leaks for Robust Sybil Detection
• Improving Gibbs Sampler Scan Quality with DoGS
• Efficient softmax approximation for GPUs
• Multichannel End-to-end Speech Recognition
• Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference
• Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data
• Count-Based Exploration with Neural Density Models
• Bidirectional learning for time-series models with hidden units
• The Price of Differential Privacy For Online Learning
• Magnetic Hamiltonian Monte Carlo
• Dropout Inference in Bayesian Neural Networks with Alpha-divergences
• Latent Intention Dialogue Models
• Robust Guarantees of Stochastic Greedy Algorithms
• Uncovering Causality from Multivariate Hawkes Integrated Cumulants
• Robust Gaussian Graphical Model Estimation with Arbitrary Corruption
• Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
• Learning Hawkes Processes from Short Doubly-Censored Event Sequences
• Pain-Free Random Differential Privacy with Sensitivity Sampling
• Probabilistic Path Hamiltonian Monte Carlo
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Discovering Discrete Latent Topics with Neural Variational Inference
• Guarantees for Greedy Maximization of Non-submodular Functions with Applications
• Cost-Optimal Learning of Causal Graphs
• Algebraic Variety Models for High-Rank Matrix Completion
• Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
• Coherent probabilistic forecasts for hierarchical time series
• Differentially Private Clustering in High-Dimensional Euclidean Spaces
• Stochastic Gradient Monomial Gamma Sampler
• Variational Dropout Sparsifies Deep Neural Networks
• Toward Controlled Generation of Text
• Robust Submodular Maximization: A Non-Uniform Partitioning Approach
• Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables
• High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm
• The Predictron: End-To-End Learning and Planning
• Soft-DTW: a Differentiable Loss Function for Time-Series
• Differentially Private Chi-squared Test by Unit Circle Mechanism
• Stochastic Gradient MCMC Methods for Hidden Markov Models
• Unimodal Probability Distributions for Deep Ordinal Classification
• Learning Continuous Semantic Representations of Symbolic Expressions
• Probabilistic Submodular Maximization in Sub-Linear Time
• Estimating individual treatment effect: generalization bounds and algorithms
• Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
• Variational Policy for Guiding Point Processes
• Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible
• Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
• Adversarial Feature Matching for Text Generation
• On Approximation Guarantees for Greedy Low Rank Optimization
• Recursive Partitioning for Personalization using Observational Data
• Optimal Densification for Fast and Accurate Minwise Hashing
• FeUdal Networks for Hierarchical Reinforcement Learning
• Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
• An Adaptive Test of Independence with Analytic Kernel Embeddings
• Distributed Batch Gaussian Process Optimization
• Dance Dance Convolution
• Language Modeling with Gated Convolutional Networks
• Deletion-Robust Submodular Maximization: Data Summarization with "the Right to be Forgotten"
• Identifying Best Interventions through Online Importance Sampling
• Stochastic Generative Hashing
• Deciding How to Decide: Dynamic Routing in Artificial Neural Networks
• Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
• Sliced Wasserstein Kernel for Persistence Diagrams
• Scalable Multi-Class Gaussian Process Classification using Expectation Propagation
• World of Bits: An Open-Domain Platform for Web-Based Agents
• Convolutional Sequence to Sequence Learning
• Analysis and Optimization of Graph Decompositions by Lifted Multicuts
• Deep IV: A Flexible Approach for Counterfactual Prediction
• ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning
• Neural Episodic Control
• End-to-End Learning for Structured Prediction Energy Networks
• Adapting Kernel Representations Online Using Submodular Maximization
• Random Feature Expansions for Deep Gaussian Processes
• Real-Time Adaptive Image Compression
• Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
• Near-Optimal Design of Experiments via Regret Minimization
• Counterfactual Data-Fusion for Online Reinforcement Learners
• Large-Scale Evolution of Image Classifiers
• Neural Optimizer Search using Reinforcement Learning
• A Unified View of Multi-Label Performance Measures
• Spherical Structured Feature Maps for Kernel Approximation
• Asynchronous Distributed Variational Gaussian Processes for Regression
• Neural Message Passing for Quantum Chemistry
• Grammar Variational Autoencoder
• Robust Budget Allocation via Continuous Submodular Functions
• Scalable Generative Models for Multi-label Learning with Missing Labels
• Nyström Method with Kernel K-means++ Samples as Landmarks
• High Dimensional Bayesian Optimization with Elastic Gaussian Process
• Accelerating Eulerian Fluid Simulation With Convolutional Networks
• Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement

Tutorials

• Distributed Deep Learning with MxNet Gluon
• Interpretable Machine Learning
• Machine Learning for Autonomous Vehicles
• Recent Advances in Stochastic Convex and Non-Convex Optimization
• Deep Reinforcement Learning, Decision Making, and Control
• Deep Learning for Health Care Applications: Challenges and Solutions
• Real World Interactive Learning
• Sequence-To-Sequence Modeling with Neural Networks
• Robustness Meets Algorithms (and Vice-Versa)

Report issues here.