icml 2016 论文列表
Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016.
|
PD-Sparse : A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification.
Noisy Activation Functions.
Slice Sampling on Hamiltonian Trajectories.
Inference Networks for Sequential Monte Carlo in Graphical Models.
Automatic Construction of Nonparametric Relational Regression Models for Multiple Time Series.
Learning Representations for Counterfactual Inference.
Correcting Forecasts with Multifactor Neural Attention.
Stochastic Discrete Clenshaw-Curtis Quadrature.
Group Equivariant Convolutional Networks.
Horizontally Scalable Submodular Maximization.
Controlling the distance to a Kemeny consensus without computing it.
Model-Free Trajectory Optimization for Reinforcement Learning.
Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters.
Shifting Regret, Mirror Descent, and Matrices.
PHOG: Probabilistic Model for Code.
Power of Ordered Hypothesis Testing.
Near Optimal Behavior via Approximate State Abstraction.
Learning Mixtures of Plackett-Luce Models.
Partition Functions from Rao-Blackwellized Tempered Sampling.
Energetic Natural Gradient Descent.
Fast Algorithms for Segmented Regression.
Epigraph projections for fast general convex programming.
Provable Algorithms for Inference in Topic Models.
Fixed Point Quantization of Deep Convolutional Networks.
Domain Adaptation with Conditional Transferable Components.
Continuous Deep Q-Learning with Model-based Acceleration.
Tensor Decomposition via Joint Matrix Schur Decomposition.
Bayesian Poisson Tucker Decomposition for Learning the Structure of International Relations.
The Label Complexity of Mixed-Initiative Classifier Training.
Control of Memory, Active Perception, and Action in Minecraft.
Conditional Dependence via Shannon Capacity: Axioms, Estimators and Applications.
ADIOS: Architectures Deep In Output Space.
Model-Free Imitation Learning with Policy Optimization.
Algorithms for Optimizing the Ratio of Submodular Functions.
Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis.
Clustering High Dimensional Categorical Data via Topographical Features.
Training Neural Networks Without Gradients: A Scalable ADMM Approach.
Robust Random Cut Forest Based Anomaly Detection on Streams.
Discriminative Embeddings of Latent Variable Models for Structured Data.
Meta-Gradient Boosted Decision Tree Model for Weight and Target Learning.
The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM.
Robust Monte Carlo Sampling using Riemannian Nosé-Poincaré Hamiltonian Dynamics.
Gromov-Wasserstein Averaging of Kernel and Distance Matrices.
Computationally Efficient Nyström Approximation using Fast Transforms.
Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity.
A Theory of Generative ConvNet.
Faster Eigenvector Computation via Shift-and-Invert Preconditioning.
Interacting Particle Markov Chain Monte Carlo.
A Kernel Test of Goodness of Fit.
A Superlinearly-Convergent Proximal Newton-type Method for the Optimization of Finite Sums.
Learning and Inference via Maximum Inner Product Search.
Speeding up k-means by approximating Euclidean distances via block vectors.
Estimation from Indirect Supervision with Linear Moments.
Pricing a Low-regret Seller.
Dynamic Capacity Networks.
Greedy Column Subset Selection: New Bounds and Distributed Algorithms.
Preconditioning Kernel Matrices.
Faster Convex Optimization: Simulated Annealing with an Efficient Universal Barrier.
Bidirectional Helmholtz Machines.
Recycling Randomness with Structure for Sublinear time Kernel Expansions.
Scalable Discrete Sampling as a Multi-Armed Bandit Problem.
Conditional Bernoulli Mixtures for Multi-label Classification.
Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity.
Geometric Mean Metric Learning.
A Box-Constrained Approach for Hard Permutation Problems.
Square Root Graphical Models: Multivariate Generalizations of Univariate Exponential Families that Permit Positive Dependencies.
Discrete Distribution Estimation under Local Privacy.
Expressiveness of Rectifier Networks.
Learning Population-Level Diffusions with Generative RNNs.
Estimating Cosmological Parameters from the Dark Matter Distribution.
Dynamic Memory Networks for Visual and Textual Question Answering.
Evasion and Hardening of Tree Ensemble Classifiers.
Generalization and Exploration via Randomized Value Functions.
Deconstructing the Ladder Network Architecture.
Recovery guarantee of weighted low-rank approximation via alternating minimization.
Principal Component Projection Without Principal Component Analysis.
Generalization Properties and Implicit Regularization for Multiple Passes SGM.
Efficient Multi-Instance Learning for Activity Recognition from Time Series Data Using an Auto-Regressive Hidden Markov Model.
Stratified Sampling Meets Machine Learning.
Early and Reliable Event Detection Using Proximity Space Representation.
Towards Faster Rates and Oracle Property for Low-Rank Matrix Estimation.
Robust Principal Component Analysis with Side Information.
Generalized Direct Change Estimation in Ising Model Structure.
A Convex Atomic-Norm Approach to Multiple Sequence Alignment and Motif Discovery.
On the Power and Limits of Distance-Based Learning.
Beyond Parity Constraints: Fourier Analysis of Hash Functions for Inference.
Markov-modulated Marked Poisson Processes for Check-in Data.
Cross-Graph Learning of Multi-Relational Associations.
Isotonic Hawkes Processes.
Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units.
Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization.
Hierarchical Decision Making In Electricity Grid Management.
Variational Inference for Monte Carlo Objectives.
Sequence to Sequence Training of CTC-RNNs with Partial Windowing.
Training Deep Neural Networks via Direct Loss Minimization.
Efficient Algorithms for Adversarial Contextual Learning.
Discrete Deep Feature Extraction: A Theory and New Architectures.
Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning.
Differentially Private Policy Evaluation.
Pliable Rejection Sampling.
Differentially Private Chi-Squared Hypothesis Testing: Goodness of Fit and Independence Testing.
How to Fake Multiply by a Gaussian Matrix.
A Convolutional Attention Network for Extreme Summarization of Source Code.
Interactive Bayesian Hierarchical Clustering.
Complex Embeddings for Simple Link Prediction.
Fast DPP Sampling for Nystrom with Application to Kernel Methods.
Mixture Proportion Estimation via Kernel Embeddings of Distributions.
The Arrow of Time in Multivariate Time Series.
Recurrent Orthogonal Networks and Long-Memory Tasks.
Persistent RNNs: Stashing Recurrent Weights On-Chip.
Learning Convolutional Neural Networks for Graphs.
Persistence weighted Gaussian kernel for topological data analysis.
Dueling Network Architectures for Deep Reinforcement Learning.
Associative Long Short-Term Memory.
BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits.
Nonparametric Canonical Correlation Analysis.
Barron and Cover's Theory in Supervised Learning and its Application to Lasso.
Nonlinear Statistical Learning with Truncated Gaussian Graphical Models.
A Simple and Strongly-Local Flow-Based Method for Cut Improvement.
Asynchronous Methods for Deep Reinforcement Learning.
Pareto Frontier Learning with Expensive Correlated Objectives.
The Sum-Product Theorem: A Foundation for Learning Tractable Models.
Graying the black box: Understanding DQNs.
Exploiting Cyclic Symmetry in Convolutional Neural Networks.
Differential Geometric Regularization for Supervised Learning of Classifiers.
Stochastic Block BFGS: Squeezing More Curvature out of Data.
Softened Approximate Policy Iteration for Markov Games.
The knockoff filter for FDR control in group-sparse and multitask regression.
Meta-Learning with Memory-Augmented Neural Networks.
On Graduated Optimization for Stochastic Non-Convex Problems.
SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization.
No penalty no tears: Least squares in high-dimensional linear models.
Opponent Modeling in Deep Reinforcement Learning.
Hierarchical Compound Poisson Factorization.
Stochastic Optimization for Multiview Representation Learning using Partial Least Squares.
Train and Test Tightness of LP Relaxations in Structured Prediction.
Gaussian quadrature for matrix inverse forms with applications.
Why Most Decisions Are Easy in Tetris - And Perhaps in Other Sequential Decision Problems, As Well.
Pixel Recurrent Neural Networks.
Dictionary Learning for Massive Matrix Factorization.
Neural Variational Inference for Text Processing.
Learning Granger Causality for Hawkes Processes.
Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors.
Fast Parameter Inference in Nonlinear Dynamical Systems using Iterative Gradient Matching.
An optimal algorithm for the Thresholding Bandit Problem.
ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission.
Recommendations as Treatments: Debiasing Learning and Evaluation.
Matrix Eigen-decomposition via Doubly Stochastic Riemannian Optimization.
Extended and Unscented Kitchen Sinks.
No-Regret Algorithms for Heavy-Tailed Linear Bandits.
Gaussian process nonparametric tensor estimator and its minimax optimality.
Black-box Optimization with a Politician.
From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification.
On collapsed representation of hierarchical Completely Random Measures.
Bounded Off-Policy Evaluation with Missing Data for Course Recommendation and Curriculum Design.
Anytime optimal algorithms in stochastic multi-armed bandits.
Simultaneous Safe Screening of Features and Samples in Doubly Sparse Modeling.
Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling.
Autoencoding beyond pixels using a learned similarity metric.
Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms.
A ranking approach to global optimization.
Optimal Classification with Multivariate Losses.
One-Shot Generalization in Deep Generative Models.
Black-Box Alpha Divergence Minimization.
Rich Component Analysis.
Predictive Entropy Search for Multi-objective Bayesian Optimization.
DR-ABC: Approximate Bayesian Computation with Kernel-Based Distribution Regression.
Deep Gaussian Processes for Regression using Approximate Expectation Propagation.
Starting Small - Learning with Adaptive Sample Sizes.
Importance Sampling Tree for Large-scale Empirical Expectation.
Auxiliary Deep Generative Models.
Extreme F-measure Maximization using Sparse Probability Estimates.
Non-negative Matrix Factorization under Heavy Noise.
Estimating Accuracy from Unlabeled Data: A Bayesian Approach.
Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control.
Solving Ridge Regression using Sketched Preconditioned SVRG.
Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions.
Ask Me Anything: Dynamic Memory Networks for Natural Language Processing.
On the Statistical Limits of Convex Relaxations.
Fast Constrained Submodular Maximization: Personalized Data Summarization.
Texture Networks: Feed-forward Synthesis of Textures and Stylized Images.
K-Means Clustering with Distributed Dimensions.
Benchmarking Deep Reinforcement Learning for Continuous Control.
On the Analysis of Complex Backup Strategies in Monte Carlo Tree Search.
Collapsed Variational Inference for Sum-Product Networks.
Distributed Clustering of Linear Bandits in Peer to Peer Networks.
Strongly-Typed Recurrent Neural Networks.
False Discovery Rate Control and Statistical Quality Assessment of Annotators in Crowdsourced Ranking.
Factored Temporal Sigmoid Belief Networks for Sequence Learning.
Variance-Reduced and Projection-Free Stochastic Optimization.
Conservative Bandits.
Contextual Combinatorial Cascading Bandits.
Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm.
Train faster, generalize better: Stability of stochastic gradient descent.
DCM Bandits: Learning to Rank with Multiple Clicks.
A Subspace Learning Approach for High Dimensional Matrix Decomposition with Efficient Column/Row Sampling.
Learning to Filter with Predictive State Inference Machines.
Learning End-to-end Video Classification with Rank-Pooling.
Learning to Generate with Memory.
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks.
Quadratic Optimization with Orthogonality Constraints: Explicit Lojasiewicz Exponent and Linear Convergence of Line-Search Methods.
A Simple and Provable Algorithm for Sparse Diagonal CCA.
The Knowledge Gradient for Sequential Decision Making with Stochastic Binary Feedbacks.
Markov Latent Feature Models.
Unitary Evolution Recurrent Neural Networks.
Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling.
Deep Structured Energy Based Models for Anomaly Detection.
Sparse Parameter Recovery from Aggregated Data.
Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives.
Dirichlet Process Mixture Model for Correcting Technical Variation in Single-Cell Gene Expression Data.
Generative Adversarial Text to Image Synthesis.
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning.
Representational Similarity Learning with Application to Brain Networks.
Estimating Maximum Expected Value through Gaussian Approximation.
Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow.
Low-rank tensor completion: a Riemannian manifold preconditioning approach.
Compressive Spectral Clustering.
L1-regularized Neural Networks are Improperly Learnable in Polynomial Time.
Structured Prediction Energy Networks.
Anytime Exploration for Multi-armed Bandits using Confidence Information.
Low-rank Solutions of Linear Matrix Equations via Procrustes Flow.
Convolutional Rectifier Networks as Generalized Tensor Decompositions.
Boolean Matrix Factorization and Noisy Completion via Message Passing.
Fast k-means with accurate bounds.
Analysis of Variational Bayesian Factorizations for Sparse and Low-Rank Estimation.
Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning.
On the Iteration Complexity of Oblivious First-Order Optimization Algorithms.
BASC: Applying Bayesian Optimization to the Search for Global Minima on Potential Energy Surfaces.
A Comparative Analysis and Study of Multiview CNN Models for Joint Object Categorization and Pose Estimation.
PAC Lower Bounds and Efficient Algorithms for The Max \(K\)-Armed Bandit Problem.
Correlation Clustering and Biclustering with Locally Bounded Errors.
A New PAC-Bayesian Perspective on Domain Adaptation.
Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms.
Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends.
Estimating Structured Vector Autoregressive Models.
PAC learning of Probabilistic Automaton based on the Method of Moments.
Online Learning with Feedback Graphs Without the Graphs.
The Information-Theoretic Requirements of Subspace Clustering with Missing Data.
Minimizing the Maximal Loss: How and Why.
Primal-Dual Rates and Certificates.
On the Quality of the Initial Basin in Overspecified Neural Networks.
A Neural Autoregressive Approach to Collaborative Filtering.
Heteroscedastic Sequences: Beyond Gaussianity.
SDCA without Duality, Regularization, and Individual Convexity.
Hyperparameter optimization with approximate gradient.
Doubly Decomposing Nonparametric Tensor Regression.
Analysis of Deep Neural Networks with Extended Data Jacobian Matrix.
Loss factorization, weakly supervised learning and label noise robustness.
Variance Reduction for Faster Non-Convex Optimization.
Community Recovery in Graphs with Locality.
Smooth Imitation Learning for Online Sequence Prediction.
Fast k-Nearest Neighbour Search via Dynamic Continuous Indexing.
Fast Rate Analysis of Some Stochastic Optimization Algorithms.
Doubly Robust Off-policy Value Evaluation for Reinforcement Learning.
Stochastic Quasi-Newton Langevin Monte Carlo.
A Self-Correcting Variable-Metric Algorithm for Stochastic Optimization.
Online Low-Rank Subspace Clustering by Basis Dictionary Pursuit.
Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification.
Exact Exponent in Optimal Rates for Crowdsourcing.
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs.
Experimental Design on a Budget for Sparse Linear Models and Applications.
A Kronecker-factored approximate Fisher matrix for convolution layers.
Network Morphism.
Learning privately from multiparty data.
Stability of Controllers for Gaussian Process Forward Models.
Optimality of Belief Propagation for Crowdsourced Classification.
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings.
A Random Matrix Approach to Echo-State Neural Networks.
Large-Margin Softmax Loss for Convolutional Neural Networks.
Parameter Estimation for Generalized Thurstone Choice Models.
Efficient Private Empirical Risk Minimization for High-dimensional Learning.
Unsupervised Deep Embedding for Clustering Analysis.
Fast methods for estimating the Numerical rank of large matrices.
Beyond CCA: Moment Matching for Multi-View Models.
Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient.
Structure Learning of Partitioned Markov Networks.
Learning Physical Intuition of Block Towers by Example.
Learning Simple Algorithms from Examples.
Actively Learning Hemimetrics with Applications to Eliciting User Preferences.
Adaptive Algorithms for Online Convex Optimization with Long-term Constraints.
Online Stochastic Linear Optimization under One-bit Feedback.
A Distributed Variational Inference Framework for Unifying Parallel Sparse Gaussian Process Regression Models.
Learning from Multiway Data: Simple and Efficient Tensor Regression.
Adaptive Sampling for SGD by Exploiting Side Information.
A Variational Analysis of Stochastic Gradient Algorithms.
Binary embeddings with structured hashed projections.
Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams.
Hierarchical Variational Models.
Stochastic Variance Reduction for Nonconvex Optimization.
Linking losses for density ratio and class-probability estimation.
Low-Rank Matrix Approximation with Stability.
Variable Elimination in the Fourier Domain.
A Kernelized Stein Discrepancy for Goodness-of-fit Tests.
Dealbreaker: A Nonlinear Latent Variable Model for Educational Data.
Convergence of Stochastic Gradient Descent for PCA.
Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity.
Accurate Robust and Efficient Error Estimation for Decision Trees.
Asymmetric Multi-task Learning based on Task Relatedness and Confidence.
Multi-Bias Non-linear Activation in Deep Neural Networks.
The Variational Nystrom method for large-scale spectral problems.
CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy.
Minimum Regret Search for Single- and Multi-Task Optimization.
On the Consistency of Feature Selection With Lasso for Non-linear Targets.
Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin.
The Information Sieve.
Multi-Player Bandits - a Musical Chairs Approach.
k-variates++: more pluses in the k-means++.
Why Regularized Auto-Encoders learn Sparse Representation?
Truthful Univariate Estimators.
The Teaching Dimension of Linear Learners.
Metadata-conscious anonymous messaging.
Dropout distillation.
Data-driven Rank Breaking for Efficient Rank Aggregation.
Hawkes Processes with Stochastic Excitations.
Additive Approximations in High Dimensional Nonparametric Regression via the SALSA.
Diversity-Promoting Bayesian Learning of Latent Variable Models.
Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization.
Revisiting Semi-Supervised Learning with Graph Embeddings.
A Deep Learning Approach to Unsupervised Ensemble Learning.
Uprooting and Rerooting Graphical Models.
Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues.
No Oops, You Won't Do It Again: Mechanisms for Self-correction in Crowdsourcing.
