icml2016.txt

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