ICML 2017 paper

参考链接

• icml 2017 acceptedPaper

Paperlist

Relative Fisher Information and Natural Gradient for Learning Large Modular Models
Priv’IT: Private and Sample Efficient Identity Testing
Being Robust (in High-Dimensions) Can Be Practical
Unifying task specification in reinforcement learning
Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for MCMC
Lost Relatives of the Gumbel Trick
Learning the Structure of Generative Models without Labeled Data
Deep Tensor Convolution on Multicores
Beyond Filters: Compact Feature Map for Portable Deep Model
Tight Bounds for Approximate Carathéodory and Beyond
Fast k-Nearest Neighbour Search via Prioritized DCI
An Adaptive Test of Independence with Analytic Kernel Embeddings
Deep Transfer Learning with Joint Adaptation Networks
Robust Probabilistic Modeling with Bayesian Data Reweighting
Distributed and Provably Good Seedings for k-Means in Constant Rounds
Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data
Combined Group and Exclusive Sparsity for Deep Neural Networks
Robust Guarantees of Stochastic Greedy Algorithms
Analysis and Optimization of Graph Decompositions by Lifted Multicuts
GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization
Curiosity-driven Exploration by Self-supervised Prediction
Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference
Consistent On-Line Off-Policy Evaluation
Coresets for Vector Summarization with Applications to Network Graphs
Oracle Complexity of Second-Order Methods for Finite-Sum Problems
Active Learning for Accurate Estimation of Linear Models
Multiple Clustering Views from Multiple Uncertain Experts
Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition
Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging
When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience Applications
Learning Deep Architectures via Generalized Whitened Neural Networks
How close are the eigenvectors and eigenvalues of the sample and actual covariance matrices?
SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization
Uncorrelation and Evenness: A New Diversity-Promoting Regularizer
Follow the Compressed Leader: Even Faster Online Learning of Eigenvectors
Faster Principal Component Regression via Optimal Polynomial Approximation to Matrix sgn(x)
Deep Spectral Clutering Learning
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
Dynamic Word Embeddings via Skip-Gram Filtering
Image-to-Markup Generation with Coarse-to-Fine Attention
Cosine Similarity Constrained Latent Space Models
Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use
Regret Minimization in Behaviorally-Constrained Zero-Sum Games
Breaking Locality Accelerates Block Gauss-Seidel
Learning to Aggregate Ordinal Labels by Maximizing Separating Width
Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data
Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence
Scalable Multi-Class Gaussian Process Classification using Expectation Propagation
Canopy --- Fast Sampling with Cover Trees
Magnetic Hamiltonian Monte Carlo
Lazifying Conditional Gradient Algorithms
Conditional Accelerated Lazy Stochastic Gradient Descent
A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates
A Semismooth Newton Method for Fast, Generic Convex Programming
Sequence Modeling via Segmentations
Evaluating Bayesian Models with Posterior Dispersion Indices
State-Frequency Memory Recurrent Neural Networks
Kernelized Tensor Factorization Machines with Applications to Neuroimaging
Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method
Self-Paced Cotraining
ChoiceRank: Identifying Preferences from Node Traffic in Networks
Unsupervised Learning by Predicting Noise
Guarantees for Greedy Maximization of Non-submodular Functions with Applications
Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates
Uniform Deviation Bounds for Unbounded Loss Functions like k-Means
Sliced Wasserstein Kernel for Persistence Diagrams
Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization
Measuring Sample Quality with Kernels
Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery
Bidirectional learning for time-series models with hidden units
Neural Message Passing for Quantum Chemistry
Stochastic modified equations and adaptive stochastic gradient algorithms
Learning Stable Stochastic Nonlinear Dynamical Systems
Post-Inference Prior Swapping
Online Learning with Local Permutations and Delayed Feedback
Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
Delta Networks for Optimized Recurrent Network Computation
Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
Spherical Structured Feature Maps for Kernel Approximation
Enumerating distinct decision trees
Dropout Inference in Bayesian Neural Networks with Alpha-divergences
Convexified Convolutional Neural Networks
Automatic Discovery of the Statistical Types of Variables in a Dataset
FeUdal Networks for Hierarchical Reinforcement Learning
Learning Hawkes Processes from Short Doubly-Censored Event Sequences
Real-Time Adaptive Image Compression
Multivariate Kernel Density Estimation: Optimal Uniform Rates
Adaptive Multiple-Arm Identification
Accelerated Stochastic Gradient Expectation-Maximization Algorithm
Modular Multitask Reinforcement Learning with Policy Sketches
Accelerating Eulerian Fluid Simulation With Convolutional Networks
An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis
Partitioned Tensor Factorizations for Learning Mixed Membership Models
Density Level Set Estimation on Manifolds with DBSCAN
Efficient Nonmypoic Active Search
High Dimensional Bayesian Optimization with Elastic Gaussian Process
Leveraging Node Attributes for Incomplete Relational Data
Tensor Decomposition with Smoothness
Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ Regret
Variational Boosting: Iteratively Refining Posterior Approximations
Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis
Tensor Decomposition via Simultaneously Power iteration
Joint Dimensionality Reduction and Metric Learning: A Geometric Take
Adaptive Sampling Probabilities for Non-Smooth Optimization
Sub-sampled Cubic Regularization for Non-convex Optimization
Asynchronous Stochastic Gradient Descent with Delay Compensation
Preferential Bayesian Optmization
Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
meProp: Minimal Effort Back Propagation for Accelerated Deep Learning
MEC: Memory-efficient Convolution for Deep Neural Network
Scaling Up Sparse Support Vector Machine by Simultaneous Feature and Sample Reduction
Bayesian inference on random simple graphs with power law degree distributions
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
Coupling Distributed and Symbolic Execution for Natural Language Queries
Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis
Learning Discrete Representations via Information Maximizing Self-Augmented Training
Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
Random Feature Expansions for Deep Gaussian Processes
A Laplacian Framework for Option Discovery in Reinforcement Learning
Gradient Projection Iterative Sketch for Large-scale Constrained Least-squares
Innovation Pursuit: A New Approach to the Subspace Clustering Problem
A Distributional Perspective on Reinforcement Learning
Efficient Algorithms for Online Non-Convex Optimization
The Price of Differential Privacy For Online Learning
On Context-Dependent Clustering of Bandits
Efficient Distributed Learning with Sparsity
A Simulated Annealing Based Inexact Oracle for Wasserstein Loss Minimization
End-to-End Differentiable Adversarial Imitation Learning
Dueling Bandits with Weak Regret
Consistent k-Clustering
(Even More) Efficient Reinforcement Learning via Posterior Sampling
Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening
Co-clustering through Optimal Transport
Just Sort It! A Simple and Effective Approach to Active Preference Learning
Depth-Width Tradeoffs in Approximating Natural Functions With Neural Networks
Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter
Nyström Method with Kernel K-Means++ Samples as Landmarks
Multi-fidelity Bayesian Optimisation with Continuous Approximations
Graph-based Isometry Invariant Representation Learning
Improved multitask learning through synaptic intelligence
Strongly-Typed Agents are Guaranteed to Interact Safely
Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks
The Shattered Gradients Problem: If resnets are the answer, then what is the question?
On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations
Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data
Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement
SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
PixelCNN models with Auxiliary Variables for Natural Image Modeling
Sharp Minima Can Generalize For Deep Nets
Evaluating the Variance of Likelihood-Ratio Gradient Estimators
Near-Optimal Design of Experiments via Regret Minimization
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Differentially Private Ordinary Least Squares
Differentially Private Learning of Graphical Models using CGMs
Leveraging Union of Subspace Structure to Improve Constrained Clustering
Learning Important Features Through Propagating Activation Differences
Probabilistic Path Hamiltonian Monte Carlo
Asymmetric Tri-training for Unsupervised Domain Adaptation
Logarithmic Time One-Against-Some
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
Identifying Best Interventions through Online Importance Sampling
Analogical Inference for Multi-relational Embeddings
Coordinated Multi-Agent Imitation Learning
Fast Bayesian Intensity Estimation for the Permanental Process
Sequence to Better Sequence: Continuous Revision of Combinatorial Structures
A Universal Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery
Zero-Inflated Exponential Family Embeddings
Clustering High Dimensional Dynamic Data Streams
Optimal Densification for Fast and Accurate Minwise Hashing
Safety-Aware Algorithms for Adversarial Contextual Bandit
Asynchronous Distributed Variational Gaussian Processes
Max-value Entropy Search for Efficient Bayesian Optimization
Tensor Balancing on Statistical Manifold
Adaptive Consensus ADMM for Distributed Optimization
Coherent probabilistic forecasts for hierarchical time series
Large-Scale Evolution of Image Classifiers
Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations
Convex Relaxation without Lifting
Differentially Private Submodular Maximization: Data Summarization in Disguise
Faster Greedy MAP Inference for Determinantal Point Processes
Diffusion Independent Semi-Bandit Influence Maximization
How to Escape Saddle Points Efficiently
Learning to Generate Long-term Future via Hierarchical Prediction
Deciding How to Decide: Dynamic Routing in Artificial Neural Networks
Parallel Multiscale Autoregressive Density Estimation
Graphical Models for Ordinal Data: A Tale of Two Approaches
Online Learning to Rank in Stochastic Click Models
Deep Voice: Real-time Neural Text-to-Speech
Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity
Stochastic Variance Reduction Methods for Policy Evaluation
An Infinite Hidden Markov Model With Similarity-Biased Transitions
Algorithmic stability and hypothesis complexity
Tensor Belief Propagation
Schema Networks
Dance Dance Convolution
Provable Optimal Algorithms for Generalized Linear Contextual Bandits
Geometry of Neural Network Loss Surfaces via Random Matrix Theory
Recurrent Highway Networks
Prediction and Control with Temporal Segment Models
Learning Continuous Semantic Representations of Symbolic Expressions
Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning
Warped Convolutions: Efficient Invariance to Spatial Transformations
RobustFill: Neural Program Learning under Noisy I/O
Dictionary Learning Based on Sparse Distribution Tomography
On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit
Learning Texture Manifolds with the Periodic Spatial GAN
Decoupled Neural Interfaces using Synthetic Gradients
Bayesian Optimization with Tree-structured Dependencies
Robust Budget Allocation via Continuous Submodular Functions
Adapting kernel representations online using submodular maximization
Minimizing Trust Leaks for Robust Sybil Detection
Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections
Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
A new formulation for deep ordinal classification
Uncovering Causality from Multivariate Hawkes Integrated Cumulants
Robust Submodular Maximization: A Non-Uniform Partitioning Approach
A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical Proficiency
Boosted Fitted Q-Iteration
Multi-objective Bandits: Optimizing the Generalized Gini Index
Understanding Black-box Predictions via Influence Functions
Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression
Zonotope hit-and-run for efficient sampling from projection DPPs
Identify the Nash Equilibrium in Static Games with Random Payoffs
AdaNet: Adaptive Structural Learning of Artificial Neural Networks
ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices
The Statistical Recurrent Unit
Optimal algorithms for smooth and strongly convex distributed optimization in networks
Equivariance Through Parameter-Sharing
Learning to learn without gradient descent by gradient descent
Local-to-Global Bayesian Network Structure Learning
Distributed Batch Gaussian Process Optimization
Multi-task Learning with Labeled and Unlabeled Tasks
SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling
A birth-death process for feature allocation
Confident Multiple Choice Learning
Failures of Gradient-Based Deep Learning
On the Sampling Problem for Kernel Quadrature
Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things
Fairness in Reinforcement Learning
Deletion-Robust Submodular Maximization: Data Summarization with "the Right to be Forgotten"
Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery
Projection-Free Distributed Online Learning in Networks
Automated Curriculum Learning for Neural Networks
Meta Networks
Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
Forward and Reverse Gradient-Based Hyperparameter Optimization
McGan: Mean and Covariance Feature Matching GAN
Learning to Discover Sparse Graphical Models
The Predictron: End-To-End Learning and Planning
A Generative Framework for Multi-label Learning with Missing Labels
Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
Algorithms for $\ell_p$ Low-Rank Approximation
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
Hierarchical Latent Feature Models for Relational Data with Side Information
Multilabel Classification with Group Testing and Codes
Distributed Mean Estimation with Limited Communication
Approximate Newton Methods and Their Local Convergence
Bayesian Boolean Matrix Factorisation
Global optimization of Lipschitz functions
Robust Gaussian Graphical Model Estimation with Arbitrary Corruption
Understanding Synthetic Gradients and Decoupled Neural Interfaces
Video Pixel Networks
Learning Determinantal Point Processes with Moments and Cycles
Frame-based Data Factorizations
Approximate Steepest Coordinate Descent
The loss surface of deep and wide neural networks
Hierarchy Through Composition with Multitask LMDPs
Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions
Pain-Free Random Differential Privacy with Sensitivity Sampling
Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms
Exact MAP Inference by Avoiding Fractional Vertices
Attentive Recurrent Comparators
DeepBach: A Steerable Model for Bach Chorales Generation
Survival HMM: An Interpretable, Event-time Prediction Model for mHealth
Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution
Multichannel End-to-end Speech Recognition
Scalable Bayesian Rule Lists
Hyperplane Clustering Via Dual Principal Component Pursuit
High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function Estimation
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
Batched High-dimensional Bayesian Optimization via Structural Kernel Learning
On orthogonality and learning RNNs with long term dependencies
High-Dimensional Structured Quantile Regression
Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling
Analytical Guarantees on Numerical Precision of Deep Neural Networks
Meritocratic Fairness for Cross-Population Selection
Neural Episodic Control
Latent Intention Dialogue Models
Cost-Optimal Learning of Causal Graphs
Local Bayesian Optimization of Motor Skills
Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks
Learning in POMDPs with Monte Carlo Tree Search
A Unified View of Multi-Label Performance Measures
Recovery Guarantees for One-hidden-layer Neural Networks
From Patches to Images: A Nonparametric Generative Model
Robust Adversarial Reinforcement Learning
Learning Infinite Layer Networks without the Kernel Trick
Differentially Private Clustering in High-Dimensional Euclidean Spaces
Accurate and Timely Real-time Prediction of Sepsis Using an End-to-end Multitask Gaussian Process RNN Classifier
Regularising Non-linear Models Using Feature Side-information
Intelligible Language Modeling with Input Switched Affine Networks
Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP
Neural networks and rational functions
Efficient softmax approximation for GPUs
Dual Supervised Learning
StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent
Improving Gibbs Sampler Scan Quality with DoGS
Stochastic Generative Hashing
Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space
Stochastic Gradient Monomial Gamma Sampler
Soft-DTW: a Differentiable Loss Function for Time-Series
Tensor-Train Recurrent Neural Networks for Video Classification
Exact Inference for Integer Latent-Variable Models
Nearly Optimal Robust Matrix Completion
Adversarial Feature Matching for Text Generation
Minimax Regret Bounds for Reinforcement LEarning
Bayesian models of data streams with Hierarchical Power Priors
Discovering Discrete Latent Topics with Neural Variational Inference
Unified Optimization Landscape for Nonconvex Low Rank Problems
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
On Kernelized Multi-armed Bandits
Learned Optimizers that Scale and Generalize
An Alternative Softmax Operator for Reinforcement Learning
Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation
Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables
Differentiable Programs with Neural Libraries
Active Heteroscedastic Regression
Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control
Consistency Analysis for Binary Classification Revisited
Multilevel Clustering via Wasserstein Means
Practical Gauss-Newton Optimisation for Deep Learning
Estimating individual treatment effect: generalization bounds and algorithms
Online Multiview Learning: Dropping Convexity for Better Efficiency
Conditional Image Synthesis with Auxiliary Classifier GANs
Variational Dropout Sparsifies Deep Neural Networks
Deep Bayesian Active Learning with Image Data
Active Learning for Cost-Sensitive Classification
Compressed Sensing using Generative Models
Deriving Neural Architectures from Sequence and Graph Kernels
Variational Policy for Guiding Point Processes
Wasserstein Generative Adversarial Networks
Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees
Selective Inference for Sparse High-Order Interaction Models
Globally Induced Forest: A Prepruning Compression Scheme
On The Projection Operator to A Three-view Cardinality Constrained Set
Diameter-Based Active Learning
Nonparanormal Information Estimation
Convolutional Sequence to Sequence Learning
Adaptive Neural Networks for Fast Test-Time Prediction
On Calibration of Modern Neural Networks
Programming with a Differentiable Forth Interpreter
Follow the Moving Leader in Deep Learning
A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions
Second-Order Kernel Online Convex Optimization with Adaptive Sketching
Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
Sequence Tutor: Conservative fine-tuning of sequence generation models with 057 003 KL-control
On Relaxing Determinism in Arithmetic Circuits
Controllable Text Generation
Latent LSTM Allocation: Joint clustering and non-linear dynamic modeling of sequence data
Recursive Partitioning for Personalization using Observational Data
Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons
Spectral Learning from a Single Trajectory under Finite-State Policies
Learning to Align the Source Code to the Compiled Object Code
Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
Multi-Class Optimal Margin Distribution Machine
Bottleneck Conditional Density Estimation
A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI
Visualizing and Understanding Multilayer Perceptron Models: A Case Study in Speech Processing
Capacity rationed diffusions for speed and locality.
Robust Structured Estimation with Single-Index Models
Stochastic Gradient MCMC Methods for Hidden Markov Models
Parseval Networks: Improving Robustness to Adversarial Examples
“Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
Input Convex Neural Networks
End-to-End Learning for Structured Prediction Energy Networks
Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization
Reinforcement Learning with Deep Energy-Based Policies
Count-Based Exploration with Neural Density Models
Probabilistic Submodular Maximization in Sub-Linear Time
On the Expressive Power of Deep Neural Networks
Neural Optimizer Search using Reinforcement Learning
World of Bits: An Open-Domain Platform for Web-Based Agents
OptNet: Differentiable Optimization as a Layer in Neural Networks
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
Interactive Learning from Policy-Dependent Human Feedback
Differentially Private Chi-squared Test by Unit Circle Mechanism
Constrained Policy Optimization