icml 2017 论文列表
Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017.
|
Online Learning to Rank in Stochastic Click Models.
Recurrent Highway Networks.
High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm.
When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience Applications.
Identify the Nash Equilibrium in Static Games with Random Payoffs.
Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values.
Recovery Guarantees for One-hidden-layer Neural Networks.
Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible.
Asynchronous Stochastic Gradient Descent with Delay Compensation.
Follow the Moving Leader in Deep Learning.
Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture.
Learning Hierarchical Features from Deep Generative Models.
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank.
Leveraging Node Attributes for Incomplete Relational Data.
Multi-Class Optimal Margin Distribution Machine.
Projection-free Distributed Online Learning in Networks.
Convexified Convolutional Neural Networks.
ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning.
Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method.
Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction.
Adversarial Feature Matching for Text Generation.
Stochastic Gradient Monomial Gamma Sampler.
Continual Learning Through Synaptic Intelligence.
Canopy Fast Sampling with Cover Trees.
Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data.
Combined Group and Exclusive Sparsity for Deep Neural Networks.
Latent Feature Lasso.
A Simulated Annealing Based Inexact Oracle for Wasserstein Loss Minimization.
Approximate Newton Methods and Their Local Convergence.
Scalable Bayesian Rule Lists.
Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity.
A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates.
Tensor-Train Recurrent Neural Networks for Video Classification.
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions.
On The Projection Operator to A Three-view Cardinality Constrained Set.
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering.
High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function Estimation.
Adaptive Consensus ADMM for Distributed Optimization.
Learning Hawkes Processes from Short Doubly-Censored Event Sequences.
Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence.
Uncorrelation and Evenness: a New Diversity-Promoting Regularizer.
Learning Latent Space Models with Angular Constraints.
Dual Supervised Learning.
A Unified View of Multi-Label Performance Measures.
Tensor Belief Propagation.
Exact Inference for Integer Latent-Variable Models.
Learned Optimizers that Scale and Generalize.
Unifying Task Specification in Reinforcement Learning.
Latent Intention Dialogue Models.
Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression.
A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery.
Beyond Filters: Compact Feature Map for Portable Deep Model.
Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms.
Variational Policy for Guiding Point Processes.
Sequence Modeling via Segmentations.
Tensor Decomposition via Simultaneous Power Iteration.
Batched High-dimensional Bayesian Optimization via Structural Kernel Learning.
Robust Probabilistic Modeling with Bayesian Data Reweighting.
Efficient Distributed Learning with Sparsity.
Max-value Entropy Search for Efficient Bayesian Optimization.
Robust Gaussian Graphical Model Estimation with Arbitrary Corruption.
Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging.
Capacity Releasing Diffusion for Speed and Locality.
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits.
Fast Bayesian Intensity Estimation for the Permanental Process.
On orthogonality and learning recurrent networks with long term dependencies.
Learning to Generate Long-term Future via Hierarchical Prediction.
Scalable Multi-Class Gaussian Process Classification using Expectation Propagation.
FeUdal Networks for Hierarchical Reinforcement Learning.
Model-Independent Online Learning for Influence Maximization.
Automatic Discovery of the Statistical Types of Variables in a Dataset.
Learning Determinantal Point Processes with Moments and Cycles.
Learning Stable Stochastic Nonlinear Dynamical Systems.
Multilabel Classification with Group Testing and Codes.
Breaking Locality Accelerates Block Gauss-Seidel.
Hyperplane Clustering via Dual Principal Component Pursuit.
Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs.
Magnetic Hamiltonian Monte Carlo.
Diameter-Based Active Learning.
Boosted Fitted Q-Iteration.
Accelerating Eulerian Fluid Simulation With Convolutional Networks.
Evaluating the Variance of Likelihood-Ratio Gradient Estimators.
An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis.
Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification.
Neural Networks and Rational Functions.
Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares.
Gradient Coding: Avoiding Stragglers in Distributed Learning.
Partitioned Tensor Factorizations for Learning Mixed Membership Models.
Coherent Probabilistic Forecasts for Hierarchical Time Series.
Selective Inference for Sparse High-Order Interaction Models.
Distributed Mean Estimation with Limited Communication.
Axiomatic Attribution for Deep Networks.
Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction.
meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting.
Relative Fisher Information and Natural Gradient for Learning Large Modular Models.
Safety-Aware Algorithms for Adversarial Contextual Bandit.
Tensor Balancing on Statistical Manifold.
Ordinal Graphical Models: A Tale of Two Approaches.
Approximate Steepest Coordinate Descent.
Probabilistic Submodular Maximization in Sub-Linear Time.
Robust Budget Allocation via Continuous Submodular Functions.
High-Dimensional Structured Quantile Regression.
Nonparanormal Information Estimation.
Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for Markov Chain Monte Carlo.
The Predictron: End-To-End Learning and Planning.
Gradient Boosted Decision Trees for High Dimensional Sparse Output.
Attentive Recurrent Comparators.
Bottleneck Conditional Density Estimation.
Optimal Densification for Fast and Accurate Minwise Hashing.
Learning Important Features Through Propagating Activation Differences.
World of Bits: An Open-Domain Platform for Web-Based Agents.
GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization.
On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit.
Differentially Private Ordinary Least Squares.
Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use.
Online Learning with Local Permutations and Delayed Feedback.
Estimating individual treatment effect: generalization bounds and algorithms.
Failures of Gradient-Based Deep Learning.
Identifying Best Interventions through Online Importance Sampling.
Developing Bug-Free Machine Learning Systems With Formal Mathematics.
Adapting Kernel Representations Online Using Submodular Maximization.
Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks.
Hierarchy Through Composition with Multitask LMDPs.
Analytical Guarantees on Numerical Precision of Deep Neural Networks.
Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data.
Asymmetric Tri-training for Unsupervised Domain Adaptation.
Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks.
Bayesian Boolean Matrix Factorisation.
Enumerating Distinct Decision Trees.
Pain-Free Random Differential Privacy with Sensitivity Sampling.
Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study.
Active Learning for Accurate Estimation of Linear Models.
Real-Time Adaptive Image Compression.
Parallel Multiscale Autoregressive Density Estimation.
Large-Scale Evolution of Image Classifiers.
Equivariance Through Parameter-Sharing.
High Dimensional Bayesian Optimization with Elastic Gaussian Process.
Innovation Pursuit: A New Approach to the Subspace Clustering Problem.
Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery.
Estimating the unseen from multiple populations.
On the Expressive Power of Deep Neural Networks.
Online and Linear-Time Attention by Enforcing Monotonic Alignments.
Neural Episodic Control.
Robust Adversarial Reinforcement Learning.
Multi-task Learning with Labeled and Unlabeled Tasks.
Geometry of Neural Network Loss Surfaces via Random Matrix Theory.
Asynchronous Distributed Variational Gaussian Process for Regression.
Curiosity-driven Exploration by Self-supervised Prediction.
Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery.
Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control.
A Birth-Death Process for Feature Allocation.
Stochastic Bouncy Particle Sampler.
Dictionary Learning Based on Sparse Distribution Tomography.
Count-Based Exploration with Neural Density Models.
Bidirectional Learning for Time-series Models with Hidden Units.
Why is Posterior Sampling Better than Optimism for Reinforcement Learning?
Algebraic Variety Models for High-Rank Matrix Completion.
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability.
The Statistical Recurrent Unit.
Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning.
Nyström Method with Kernel K-means++ Samples as Landmarks.
Conditional Image Synthesis with Auxiliary Classifier GANs.
Multichannel End-to-end Speech Recognition.
Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data.
SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient.
The Loss Surface of Deep and Wide Neural Networks.
Post-Inference Prior Swapping.
Delta Networks for Optimized Recurrent Network Computation.
Adaptive Sampling Probabilities for Non-Smooth Optimization.
Understanding the Representation and Computation of Multilayer Perceptrons: A Case Study in Speech Recognition.
Meta Networks.
Variants of RMSProp and Adagrad with Logarithmic Regret Bounds.
Sequence to Better Sequence: Continuous Revision of Combinatorial Structures.
McGan: Mean and Covariance Feature Matching GAN.
Coupling Distributed and Symbolic Execution for Natural Language Queries.
Regularising Non-linear Models Using Feature Side-information.
Variational Dropout Sparsifies Deep Neural Networks.
Active Learning for Top-K Rank Aggregation from Noisy Comparisons.
Differentially Private Submodular Maximization: Data Summarization in Disguise.
Improving Gibbs Sampler Scan Quality with DoGS.
Prediction and Control with Temporal Segment Models.
Deletion-Robust Submodular Maximization: Data Summarization with "the Right to be Forgotten".
Tight Bounds for Approximate Carathéodory and Beyond.
Device Placement Optimization with Reinforcement Learning.
Variational Boosting: Iteratively Refining Posterior Approximations.
Discovering Discrete Latent Topics with Neural Variational Inference.
Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections.
Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks.
Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates.
Risk Bounds for Transferring Representations With and Without Fine-Tuning.
Deciding How to Decide: Dynamic Routing in Artificial Neural Networks.
ChoiceRank: Identifying Preferences from Node Traffic in Networks.
Just Sort It! A Simple and Effective Approach to Active Preference Learning.
Bayesian Models of Data Streams with Hierarchical Power Priors.
On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations.
Global optimization of Lipschitz functions.
Frame-based Data Factorizations.
A Laplacian Framework for Option Discovery in Reinforcement Learning.
Interactive Learning from Policy-Dependent Human Feedback.
Self-Paced Co-training.
Stochastic Gradient MCMC Methods for Hidden Markov Models.
Spherical Structured Feature Maps for Kernel Approximation.
Learning Gradient Descent: Better Generalization and Longer Horizons.
Learning Deep Architectures via Generalized Whitened Neural Networks.
How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?
Multiplicative Normalizing Flows for Variational Bayesian Neural Networks.
Deep Transfer Learning with Joint Adaptation Networks.
Learning Infinite Layer Networks Without the Kernel Trick.
Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling.
Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization.
Analogical Inference for Multi-relational Embeddings.
Algorithmic Stability and Hypothesis Complexity.
Iterative Machine Teaching.
Zero-Inflated Exponential Family Embeddings.
Leveraging Union of Subspace Structure to Improve Constrained Clustering.
Exact MAP Inference by Avoiding Fractional Vertices.
Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization.
Stochastic Modified Equations and Adaptive Stochastic Gradient Algorithms.
Forest-type Regression with General Losses and Robust Forest.
Fast k-Nearest Neighbour Search via Prioritized DCI.
Provably Optimal Algorithms for Generalized Linear Contextual Bandits.
Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations.
Dropout Inference in Bayesian Neural Networks with Alpha-divergences.
Learning to Align the Source Code to the Compiled Object Code.
Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization.
Deriving Neural Architectures from Sequence and Graph Kernels.
Confident Multiple Choice Learning.
Bayesian inference on random simple graphs with power law degree distributions.
Coordinated Multi-Agent Imitation Learning.
Deep Spectral Clustering Learning.
Consistent k-Clustering.
Conditional Accelerated Lazy Stochastic Gradient Descent.
Co-clustering through Optimal Transport.
Grammar Variational Autoencoder.
Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things.
Evaluating Bayesian Models with Posterior Dispersion Indices.
Active Learning for Cost-Sensitive Classification.
PixelCNN Models with Auxiliary Variables for Natural Image Modeling.
Sub-sampled Cubic Regularization for Non-convex Optimization.
Understanding Black-box Predictions via Influence Functions.
Cost-Optimal Learning of Causal Graphs.
SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization.
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks.
Graph-based Isometry Invariant Representation Learning.
On Approximation Guarantees for Greedy Low Rank Optimization.
Meritocratic Fairness for Cross-Population Selection.
Learning in POMDPs with Monte Carlo Tree Search.
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics.
Multi-fidelity Bayesian Optimisation with Continuous Approximations.
Recursive Partitioning for Personalization using Observational Data.
Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP.
Video Pixel Networks.
Differentially Private Chi-squared Test by Unit Circle Mechanism.
StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent.
An Adaptive Test of Independence with Analytic Kernel Embeddings.
Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs.
How to Escape Saddle Points Efficiently.
Efficient Nonmyopic Active Search.
Contextual Decision Processes with low Bellman rank are PAC-Learnable.
Uniform Convergence Rates for Kernel Density Estimation.
Density Level Set Estimation on Manifolds with DBSCAN.
From Patches to Images: A Nonparametric Generative Model.
Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation.
Bayesian Optimization with Tree-structured Dependencies.
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control.
Scalable Generative Models for Multi-label Learning with Missing Labels.
Decoupled Neural Interfaces using Synthetic Gradients.
Fairness in Reinforcement Learning.
Variational Inference for Sparse and Undirected Models.
Tensor Decomposition with Smoothness.
Toward Controlled Generation of Text.
Deep Generative Models for Relational Data with Side Information.
State-Frequency Memory Recurrent Neural Networks.
Learning Discrete Representations via Information Maximizing Self-Augmented Training.
Dissipativity Theory for Nesterov's Accelerated Method.
Analysis and Optimization of Graph Decompositions by Lifted Multicuts.
Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks.
Minimizing Trust Leaks for Robust Sybil Detection.
Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo.
Multilevel Clustering via Wasserstein Means.
SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling.
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning.
Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space.
Warped Convolutions: Efficient Invariance to Spatial Transformations.
The Sample Complexity of Online One-Class Collaborative Filtering.
Kernelized Support Tensor Machines.
Efficient Regret Minimization in Non-Convex Games.
Robust Guarantees of Stochastic Greedy Algorithms.
Deep IV: A Flexible Approach for Counterfactual Prediction.
Joint Dimensionality Reduction and Metric Learning: A Geometric Take.
Data-Efficient Policy Evaluation Through Behavior Policy Search.
Faster Greedy MAP Inference for Determinantal Point Processes.
Consistent On-Line Off-Policy Evaluation.
DeepBach: a Steerable Model for Bach Chorales Generation.
Reinforcement Learning with Deep Energy-Based Policies.
Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs.
ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices.
On Calibration of Modern Neural Networks.
Automated Curriculum Learning for Neural Networks.
Efficient softmax approximation for GPUs.
Measuring Sample Quality with Kernels.
Preferential Bayesian Optimization.
Convex Phase Retrieval without Lifting via PhaseMax.
Neural Message Passing for Quantum Chemistry.
On Context-Dependent Clustering of Bandits.
Convolutional Sequence to Sequence Learning.
No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis.
Zonotope Hit-and-run for Efficient Sampling from Projection DPPs.
Differentiable Programs with Neural Libraries.
Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis.
Local-to-Global Bayesian Network Structure Learning.
Deep Bayesian Active Learning with Image Data.
Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier.
Forward and Reverse Gradient-Based Hyperparameter Optimization.
Counterfactual Data-Fusion for Online Reinforcement Learners.
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning.
Input Switched Affine Networks: An RNN Architecture Designed for Interpretability.
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.
Coresets for Vector Summarization with Applications to Network Graphs.
Regret Minimization in Behaviorally-Constrained Zero-Sum Games.
Fake News Mitigation via Point Process Based Intervention.
Maximum Selection and Ranking under Noisy Comparisons.
Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening.
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders.
Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement.
Stochastic Variance Reduction Methods for Policy Evaluation.
Dance Dance Convolution.
A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI.
Sharp Minima Can Generalize For Deep Nets.
Probabilistic Path Hamiltonian Monte Carlo.
Being Robust (in High Dimensions) Can Be Practical.
RobustFill: Neural Program Learning under Noisy I/O.
Image-to-Markup Generation with Coarse-to-Fine Attention.
iSurvive: An Interpretable, Event-time Prediction Model for mHealth.
Consistency Analysis for Binary Classification Revisited.
Distributed Batch Gaussian Process Optimization.
An Infinite Hidden Markov Model With Similarity-Biased Transitions.
Language Modeling with Gated Convolutional Networks.
Logarithmic Time One-Against-Some.
Stochastic Generative Hashing.
Understanding Synthetic Gradients and Decoupled Neural Interfaces.
Soft-DTW: a Differentiable Loss Function for Time-Series.
Random Feature Expansions for Deep Gaussian Processes.
AdaNet: Adaptive Structural Learning of Artificial Neural Networks.
Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC.
Parseval Networks: Improving Robustness to Adversarial Examples.
On Kernelized Multi-armed Bandits.
Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution.
On Relaxing Determinism in Arithmetic Circuits.
MEC: Memory-efficient Convolution for Deep Neural Network.
Algorithms for $\ell_p$ Low-Rank Approximation.
Nearly Optimal Robust Matrix Completion.
Learning to Aggregate Ordinal Labels by Maximizing Separating Width.
Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability.
Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data.
Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables.
Learning to Learn without Gradient Descent by Gradient Descent.
Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions.
Dueling Bandits with Weak Regret.
Adaptive Multiple-Arm Identification.
Robust Structured Estimation with Single-Index Models.
Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning.
Active Heteroscedastic Regression.
Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference.
Multiple Clustering Views from Multiple Uncertain Experts.
Sliced Wasserstein Kernel for Persistence Diagrams.
"Convex Until Proven Guilty": Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions.
Second-Order Kernel Online Convex Optimization with Adaptive Sketching.
Priv'IT: Private and Sample Efficient Identity Testing.
Multi-objective Bandits: Optimizing the Generalized Gini Index.
Deep Tensor Convolution on Multicores.
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs.
Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning.
On the Sampling Problem for Kernel Quadrature.
Clustering High Dimensional Dynamic Data Streams.
Lazifying Conditional Gradient Algorithms.
Practical Gauss-Newton Optimisation for Deep Learning.
Programming with a Differentiable Forth Interpreter.
Compressed Sensing using Generative Models.
Adaptive Neural Networks for Efficient Inference.
Unsupervised Learning by Predicting Noise.
Robust Submodular Maximization: A Non-Uniform Partitioning Approach.
Guarantees for Greedy Maximization of Non-submodular Functions with Applications.
Efficient Online Bandit Multiclass Learning with Õ(√T) Regret.
Differentially Private Learning of Undirected Graphical Models Using Collective Graphical Models.
Learning Texture Manifolds with the Periodic Spatial GAN.
Neural Optimizer Search with Reinforcement Learning.
A Distributional Perspective on Reinforcement Learning.
Learning to Discover Sparse Graphical Models.
End-to-End Learning for Structured Prediction Energy Networks.
Globally Induced Forest: A Prepruning Compression Scheme.
Unimodal Probability Distributions for Deep Ordinal Classification.
Emulating the Expert: Inverse Optimization through Online Learning.
End-to-End Differentiable Adversarial Imitation Learning.
Dynamic Word Embeddings.
Lost Relatives of the Gumbel Trick.
Spectral Learning from a Single Trajectory under Finite-State Policies.
Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks.
The Shattered Gradients Problem: If resnets are the answer, then what is the question?
Strongly-Typed Agents are Guaranteed to Interact Safely.
Differentially Private Clustering in High-Dimensional Euclidean Spaces.
Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms.
Learning Algorithms for Active Learning.
Distributed and Provably Good Seedings for k-Means in Constant Rounds.
Uniform Deviation Bounds for k-Means Clustering.
Learning the Structure of Generative Models without Labeled Data.
Minimax Regret Bounds for Reinforcement Learning.
Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees.
An Alternative Softmax Operator for Reinforcement Learning.
A Closer Look at Memorization in Deep Networks.
Generalization and Equilibrium in Generative Adversarial Nets (GANs).
Wasserstein Generative Adversarial Networks.
Oracle Complexity of Second-Order Methods for Finite-Sum Problems.
Deep Voice: Real-time Neural Text-to-Speech.
A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical Proficiency.
Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning.
Modular Multitask Reinforcement Learning with Policy Sketches.
An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation.
Input Convex Neural Networks.
OptNet: Differentiable Optimization as a Layer in Neural Networks.
Near-Optimal Design of Experiments via Regret Minimization.
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU.
Faster Principal Component Regression and Stable Matrix Chebyshev Approximation.
Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition.
Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex Parameter.
Learning Continuous Semantic Representations of Symbolic Expressions.
A Semismooth Newton Method for Fast, Generic Convex Programming.
Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis.
Connected Subgraph Detection with Mirror Descent on SDPs.
Local Bayesian Optimization of Motor Skills.
The Price of Differential Privacy for Online Learning.
Constrained Policy Optimization.
A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions.
Uncovering Causality from Multivariate Hawkes Integrated Cumulants.
