Downloads 2017

Format:
Posters:
Tutorials:
Invited talks:
Workshops:
Demonstrations:

Number of events: 470

A Birth-Death Process for Feature Allocation
Accelerating Eulerian Fluid Simulation With Convolutional Networks
A Closer Look at Memorization in Deep Networks
Active Heteroscedastic Regression
Active Learning for Accurate Estimation of Linear Models
Active Learning for Cost-Sensitive Classification
Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons
AdaNet: Adaptive Structural Learning of Artificial Neural Networks
Adapting Kernel Representations Online Using Submodular Maximization
Adaptive Consensus ADMM for Distributed Optimization
Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP
Adaptive Multiple-Arm Identification
Adaptive Neural Networks for Efficient Inference
Adaptive Sampling Probabilities for Non-Smooth Optimization
A Distributional Perspective on Reinforcement Learning
A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI
Adversarial Feature Matching for Text Generation
Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
A Laplacian Framework for Option Discovery in Reinforcement Learning
Algebraic Variety Models for High-Rank Matrix Completion
Algorithmic Stability and Hypothesis Complexity
Algorithms for $\ell_p$ Low-Rank Approximation
An Adaptive Test of Independence with Analytic Kernel Embeddings
Analogical Inference for Multi-relational Embeddings
An Alternative Softmax Operator for Reinforcement Learning
Analysis and Optimization of Graph Decompositions by Lifted Multicuts
Analytical Guarantees on Numerical Precision of Deep Neural Networks
An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis
An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation
An Infinite Hidden Markov Model With Similarity-Biased Transitions
Approximate Newton Methods and Their Local Convergence
Approximate Steepest Coordinate Descent
A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates
A Semismooth Newton Method for Fast, Generic Convex Programming
A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical Proficiency
A Simulated Annealing Based Inexact Oracle for Wasserstein Loss Minimization
Asymmetric Tri-training for Unsupervised Domain Adaptation
Asynchronous Distributed Variational Gaussian Processes for Regression
Asynchronous Distributed Variational Gaussian Processes for Regresssion
Asynchronous Stochastic Gradient Descent with Delay Compensation
Attentive Recurrent Comparators
A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions
A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery
A Unified View of Multi-Label Performance Measures
Automated Curriculum Learning for Neural Networks
Automatic Discovery of the Statistical Types of Variables in a Dataset
Automatic Machine Learning (AutoML 2017)
Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
Axiomatic Attribution for Deep Networks
Batched High-dimensional Bayesian Optimization via Structural Kernel Learning
Bayesian Boolean Matrix Factorisation
Bayesian inference on random simple graphs with power law degree distributions
Bayesian Models of Data Streams with Hierarchical Power Priors
Bayesian Optimization with Tree-structured Dependencies
Being Robust (in High Dimensions) Can Be Practical
Beyond Filters: Compact Feature Map for Portable Deep Model
Bidirectional learning for time-series models with hidden units
Boosted Fitted Q-Iteration
Bottleneck Conditional Density Estimation
Breaking Locality Accelerates Block Gauss-Seidel
Canopy --- Fast Sampling with Cover Trees
Capacity Releasing Diffusion for Speed and Locality.
Causal Learning
ChoiceRank: Identifying Preferences from Node Traffic in Networks
Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery
Clustering High Dimensional Dynamic Data Streams
Co-clustering through Optimal Transport
Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery
Coherent probabilistic forecasts for hierarchical time series
Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible
Combined Group and Exclusive Sparsity for Deep Neural Networks
Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning
Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis
Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data
Compressed Sensing using Generative Models
Conditional Accelerated Lazy Stochastic Gradient Descent
Conditional Image Synthesis with Auxiliary Classifier GANs
Confident Multiple Choice Learning
Connected Subgraph Detection with Mirror Descent on SDPs
Consistency Analysis for Binary Classification Revisited
Consistent k-Clustering
Consistent On-Line Off-Policy Evaluation
Constrained Policy Optimization
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Continual Learning Through Synaptic Intelligence
Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization
Convexified Convolutional Neural Networks
Convex Phase Retrieval without Lifting via PhaseMax
“Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions
Convolutional Sequence to Sequence Learning
Coordinated Multi-Agent Imitation Learning
Coresets for Vector Summarization with Applications to Network Graphs
Cost-Optimal Learning of Causal Graphs
Count-Based Exploration with Neural Density Models
Counterfactual Data-Fusion for Online Reinforcement Learners
Coupling Distributed and Symbolic Execution for Natural Language Queries
Curiosity-driven Exploration by Self-supervised Prediction
Dance Dance Convolution
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
Data-Efficient Policy Evaluation Through Behavior Policy Search
Deciding How to Decide: Dynamic Routing in Artificial Neural Networks
Decoupled Neural Interfaces using Synthetic Gradients
DeepBach: a Steerable Model for Bach Chorales Generation
Deep Bayesian Active Learning with Image Data
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
Deep Generative Models for Relational Data with Side Information
Deep IV: A Flexible Approach for Counterfactual Prediction
Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
Deep Learning for Health Care Applications: Challenges and Solutions
Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
Deep Reinforcement Learning, Decision Making, and Control
Deep Spectral Clustering Learning
Deep Structured Prediction
Deep Tensor Convolution on Multicores
Deep Transfer Learning with Joint Adaptation Networks
Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
Deep Voice: Real-time Neural Text-to-Speech
Deletion-Robust Submodular Maximization: Data Summarization with "the Right to be Forgotten"
Delta Networks for Optimized Recurrent Network Computation
Density Level Set Estimation on Manifolds with DBSCAN
Depth-Width Tradeoffs in Approximating Natural Functions With Neural Networks
Deriving Neural Architectures from Sequence and Graph Kernels
Developing Bug-Free Machine Learning Systems With Formal Mathematics
Device Placement Optimization with Reinforcement Learning
Diameter-Based Active Learning
Dictionary Learning Based on Sparse Distribution Tomography
Differentiable Programs with Neural Libraries
Differentially Private Chi-squared Test by Unit Circle Mechanism
Differentially Private Clustering in High-Dimensional Euclidean Spaces
Differentially Private Learning of Graphical Models using CGMs
Differentially Private Ordinary Least Squares
Differentially Private Submodular Maximization: Data Summarization in Disguise
Discovering Discrete Latent Topics with Neural Variational Inference
Dissipativity Theory for Nesterov's Accelerated Method
Distributed and Provably Good Seedings for k-Means in Constant Rounds
Distributed Batch Gaussian Process Optimization
Distributed Deep Learning with MxNet Gluon
Distributed Mean Estimation with Limited Communication
Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition
Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization
Dropout Inference in Bayesian Neural Networks with Alpha-divergences
Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization
Dual Supervised Learning
Dueling Bandits with Weak Regret
Dynamic Word Embeddings
Efficient Distributed Learning with Sparsity
Efficient Nonmyopic Active Search
Efficient Online Bandit Multiclass Learning with O(sqrt{T}) Regret
Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections
Efficient Regret Minimization in Non-Convex Games
Efficient softmax approximation for GPUs
Emulating the Expert: Inverse Optimization through Online Learning
End-to-End Differentiable Adversarial Imitation Learning
End-to-End Learning for Structured Prediction Energy Networks
Enumerating Distinct Decision Trees
Equivariance Through Parameter-Sharing
Estimating individual treatment effect: generalization bounds and algorithms
Estimating the unseen from multiple populations
Evaluating Bayesian Models with Posterior Dispersion Indices
Evaluating the Variance of Likelihood-Ratio Gradient Estimators
Exact Inference for Integer Latent-Variable Models
Exact MAP Inference by Avoiding Fractional Vertices
Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
Failures of Gradient-Based Deep Learning
Fairness in Reinforcement Learning
Fake News Mitigation via Point Process Based Intervention
Fast Bayesian Intensity Estimation for the Permanental Process
Faster Greedy MAP Inference for Determinantal Point Processes
Faster Principal Component Regression and Stable Matrix Chebyshev Approximation
Fast k-Nearest Neighbour Search via Prioritized DCI
FeUdal Networks for Hierarchical Reinforcement Learning
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU
Follow the Moving Leader in Deep Learning
Forest-type Regression with General Losses and Robust Forest
Forward and Reverse Gradient-Based Hyperparameter Optimization
Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for MCMC
Frame-based Data Factorizations
From Patches to Images: A Nonparametric Generative Model
Generalization and Equilibrium in Generative Adversarial Nets (GANs)
Genomics, Big Data, and Machine Learning: Understanding the Human Wiring Diagram and Driving the Healthcare Revolution
Geometry of Neural Network Loss Surfaces via Random Matrix Theory
Globally Induced Forest: A Prepruning Compression Scheme
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
Global optimization of Lipschitz functions
Gradient Boosted Decision Trees for High Dimensional Sparse Output
Gradient Coding: Avoiding Stragglers in Distributed Learning
Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares
Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling
Grammar Variational Autoencoder
Graph-based Isometry Invariant Representation Learning
GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization
Guarantees for Greedy Maximization of Non-submodular Functions with Applications
Hierarchy Through Composition with Multitask LMDPs
High Dimensional Bayesian Optimization with Elastic Gaussian Process
High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function Estimation
High-Dimensional Structured Quantile Regression
High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm
How AI Designers will Dictate Our Civic Future
How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?
How to Escape Saddle Points Efficiently
Human in the Loop Machine Learning
Hyperplane Clustering Via Dual Principal Component Pursuit
ICML Workshop on Machine Learning for Autonomous Vehicles 2017
Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables
Identifying Best Interventions through Online Importance Sampling
Identify the Nash Equilibrium in Static Games with Random Payoffs
Image-to-Markup Generation with Coarse-to-Fine Attention
Implicit Generative Models
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
Improving Gibbs Sampler Scan Quality with DoGS
Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution
Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms
Innovation Pursuit: A New Approach to the Subspace Clustering Problem
Input Convex Neural Networks
Input Switched Affine Networks: An RNN Architecture Designed for Interpretability
Interactive Learning from Policy-Dependent Human Feedback
Interactive Machine Learning and Semantic Information Retrieval
Interpretable Machine Learning
iSurvive: An Interpretable, Event-time Prediction Model for mHealth
Iterative Machine Teaching
Joint Dimensionality Reduction and Metric Learning: A Geometric Take
Just Sort It! A Simple and Effective Approach to Active Preference Learning
Kernelized Support Tensor Machines
Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
Language Modeling with Gated Convolutional Networks
Large-Scale Evolution of Image Classifiers
Latent Feature Lasso
Latent Intention Dialogue Models
Latent LSTM Allocation: Joint clustering and non-linear dynamic modeling of sequence data
Lazifying Conditional Gradient Algorithms
Learned Optimizers that Scale and Generalize
Learning Algorithms for Active Learning
Learning Continuous Semantic Representations of Symbolic Expressions
Learning Deep Architectures via Generalized Whitened Neural Networks
Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo
Learning Determinantal Point Processes with Moments and Cycles
Learning Discrete Representations via Information Maximizing Self-Augmented Training
Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis
Learning Gradient Descent: Better Generalization and Longer Horizons
Learning Hawkes Processes from Short Doubly-Censored Event Sequences
Learning Hierarchical Features from Deep Generative Models
Learning Important Features Through Propagating Activation Differences
Learning Infinite Layer Networks without the Kernel Trick
Learning in POMDPs with Monte Carlo Tree Search
Learning Latent Space Models with Angular Constraints
Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture
Learning Stable Stochastic Nonlinear Dynamical Systems
Learning Texture Manifolds with the Periodic Spatial GAN
Learning the Structure of Generative Models without Labeled Data
Learning to Aggregate Ordinal Labels by Maximizing Separating Width
Learning to Align the Source Code to the Compiled Object Code
Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
Learning to Discover Sparse Graphical Models
Learning to Generate Long-term Future via Hierarchical Prediction
Learning to Generate Natural Language
Learning to Learn without Gradient Descent by Gradient Descent
Leveraging Node Attributes for Incomplete Relational Data
Leveraging Union of Subspace Structure to Improve Constrained Clustering
Lifelong Learning: A Reinforcement Learning Approach
Local Bayesian Optimization of Motor Skills
Local-to-Global Bayesian Network Structure Learning
Logarithmic Time One-Against-Some
Lost Relatives of the Gumbel Trick
Machine Learning for Autonomous Vehicles
Machine Learning for Music Discovery
Machine Learning in Speech and Language Processing
Magnetic Hamiltonian Monte Carlo
Maximum Selection and Ranking under Noisy Comparisons
Max-value Entropy Search for Efficient Bayesian Optimization
McGan: Mean and Covariance Feature Matching GAN
Measuring Sample Quality with Kernels
MEC: Memory-efficient Convolution for Deep Neural Network
meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting
Meritocratic Fairness for Cross-Population Selection
Meta Networks
Minimax Regret Bounds for Reinforcement Learning
Minimizing Trust Leaks for Robust Sybil Detection
ML on a budget: IoT, Mobile and other tiny-ML applications
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Model-Independent Online Learning for Influence Maximization
Modular Multitask Reinforcement Learning with Policy Sketches
Multichannel End-to-end Speech Recognition
Multi-Class Optimal Margin Distribution Machine
Multi-fidelity Bayesian Optimisation with Continuous Approximations
Multilabel Classification with Group Testing and Codes
Multilevel Clustering via Wasserstein Means
Multi-objective Bandits: Optimizing the Generalized Gini Index
Multiple Clustering Views from Multiple Uncertain Experts
Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
Multi-task Learning with Labeled and Unlabeled Tasks
Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter
Nearly Optimal Robust Matrix Completion
Near-Optimal Design of Experiments via Regret Minimization
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
Neural Episodic Control
Neural Message Passing for Quantum Chemistry
Neural networks and rational functions
Neural Optimizer Search using Reinforcement Learning
Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks
Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates
Nonparanormal Information Estimation
No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis
Nyström Method with Kernel K-means++ Samples as Landmarks
On Approximation Guarantees for Greedy Low Rank Optimization
On Calibration of Modern Neural Networks
On Context-Dependent Clustering of Bandits
On Kernelized Multi-armed Bandits
Online and Linear-Time Attention by Enforcing Monotonic Alignments
Online Learning to Rank in Stochastic Click Models
Online Learning with Local Permutations and Delayed Feedback
Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability
On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations
On orthogonality and learning RNNs with long term dependencies
On Relaxing Determinism in Arithmetic Circuits
On the Expressive Power of Deep Neural Networks
On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit
On The Projection Operator to A Three-view Cardinality Constrained Set
On the Sampling Problem for Kernel Quadrature
Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
Optimal Densification for Fast and Accurate Minwise Hashing
OptNet: Differentiable Optimization as a Layer in Neural Networks
Oracle Complexity of Second-Order Methods for Finite-Sum Problems
Ordinal Graphical Models: A Tale of Two Approaches
Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use
Pain-Free Random Differential Privacy with Sensitivity Sampling
Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space
Parallel Multiscale Autoregressive Density Estimation
Parseval Networks: Improving Robustness to Adversarial Examples
Partitioned Tensor Factorizations for Learning Mixed Membership Models
Picky Learners: Choosing Alternative Ways to Process Data.
PixelCNN Models with Auxiliary Variables for Natural Image Modeling
Post-Inference Prior Swapping
Practical Gauss-Newton Optimisation for Deep Learning
Prediction and Control with Temporal Segment Models
Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control
Preferential Bayesian Optmization
Principled Approaches to Deep Learning
Private and Secure Machine Learning
Priv’IT: Private and Sample Efficient Identity Testing
Probabilistic Path Hamiltonian Monte Carlo
Probabilistic Submodular Maximization in Sub-Linear Time
Programming with a Differentiable Forth Interpreter
Projection-free Distributed Online Learning in Networks
ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices
Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations
Provably Optimal Algorithms for Generalized Linear Contextual Bandits
Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks
Random Feature Expansions for Deep Gaussian Processes
Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees
Real-Time Adaptive Image Compression
Real World Interactive Learning
Recent Advances in Stochastic Convex and Non-Convex Optimization
Recovery Guarantees for One-hidden-layer Neural Networks
Recurrent Highway Networks
Recursive Partitioning for Personalization using Observational Data
Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning
Regret Minimization in Behaviorally-Constrained Zero-Sum Games
Regularising Non-linear Models Using Feature Side-information
Reinforcement Learning with Deep Energy-Based Policies
Reinforcement Learning Workshop
Relative Fisher Information and Natural Gradient for Learning Large Modular Models
Reliable Machine Learning in the Wild
Reproducibility in Machine Learning Research
Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method
Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things
Risk Bounds for Transferring Representations With and Without Fine-Tuning
Robust Adversarial Reinforcement Learning
Robust Budget Allocation via Continuous Submodular Functions
RobustFill: Neural Program Learning under Noisy I/O
Robust Gaussian Graphical Model Estimation with Arbitrary Corruption
Robust Guarantees of Stochastic Greedy Algorithms
Robustness Meets Algorithms (and Vice-Versa)
Robust Probabilistic Modeling with Bayesian Data Reweighting
Robust Structured Estimation with Single-Index Models
Robust Submodular Maximization: A Non-Uniform Partitioning Approach
Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement
Safety-Aware Algorithms for Adversarial Contextual Bandit
SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
Scalable Bayesian Rule Lists
Scalable Generative Models for Multi-label Learning with Missing Labels
Scalable Multi-Class Gaussian Process Classification using Expectation Propagation
Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
Second-Order Kernel Online Convex Optimization with Adaptive Sketching
Selective Inference for Sparse High-Order Interaction Models
Self-Paced Co-training
Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data
Sequence Modeling via Segmentations
Sequence to Better Sequence: Continuous Revision of Combinatorial Structures
Sequence-To-Sequence Modeling with Neural Networks
Sequence Tutor: Conservative fine-tuning of sequence generation models with KL-control
Sharp Minima Can Generalize For Deep Nets
Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation
Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging
Sliced Wasserstein Kernel for Persistence Diagrams
Soft-DTW: a Differentiable Loss Function for Time-Series
Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression
Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity
Spectral Learning from a Single Trajectory under Finite-State Policies
Spherical Structured Feature Maps for Kernel Approximation
SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling
SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
State-Frequency Memory Recurrent Neural Networks
Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening
StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent
Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values
Stochastic Bouncy Particle Sampler
Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence
Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification
Stochastic Generative Hashing
Stochastic Gradient MCMC Methods for Hidden Markov Models
Stochastic Gradient Monomial Gamma Sampler
Stochastic modified equations and adaptive stochastic gradient algorithms
Stochastic Variance Reduction Methods for Policy Evaluation
Strongly-Typed Agents are Guaranteed to Interact Safely
Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions
Sub-sampled Cubic Regularization for Non-convex Optimization
Tensor Balancing on Statistical Manifold
Tensor Belief Propagation
Tensor Decomposition via Simultaneous Power Iteration
Tensor Decomposition with Smoothness
Tensor-Train Recurrent Neural Networks for Video Classification
The loss surface of deep and wide neural networks
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
The Predictron: End-To-End Learning and Planning
The Price of Differential Privacy For Online Learning
The Sample Complexity of Online One-Class Collaborative Filtering
The Shattered Gradients Problem: If resnets are the answer, then what is the question?
The Statistical Recurrent Unit
Tight Bounds for Approximate Carathéodory and Beyond
Time Series Workshop
Toward Controlled Generation of Text
Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
Towards Reinforcement Learning in the Real World
Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference
Uncorrelation and Evenness: a New Diversity-Promoting Regularizer
Uncovering Causality from Multivariate Hawkes Integrated Cumulants
Understanding Black-box Predictions via Influence Functions
Understanding Synthetic Gradients and Decoupled Neural Interfaces
Uniform Convergence Rates for Kernel Density Estimation
Uniform Deviation Bounds for k-Means Clustering
Unifying task specification in reinforcement learning
Unimodal Probability Distributions for Deep Ordinal Classification
Unsupervised Learning by Predicting Noise
Variants of RMSProp and Adagrad with Logarithmic Regret Bounds
Variational Boosting: Iteratively Refining Posterior Approximations
Variational Dropout Sparsifies Deep Neural Networks
Variational Inference for Sparse and Undirected Models
Variational Policy for Guiding Point Processes
Video Games and Machine Learning
Video Pixel Networks
Visualizing and Understanding Multilayer Perceptron Models: A Case Study in Speech Processing
Warped Convolutions: Efficient Invariance to Spatial Transformations
Wasserstein Generative Adversarial Networks
When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience Applications
Why is Posterior Sampling Better than Optimism for Reinforcement Learning?
Workshop on Computational Biology
Workshop on Human Interpretability in Machine Learning (WHI)
Workshop on Visualization for Deep Learning
World of Bits: An Open-Domain Platform for Web-Based Agents
Zero-Inflated Exponential Family Embeddings
Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning
Zonotope hit-and-run for efficient sampling from projection DPPs