International Conference on Machine Learning (ICML) - 2015

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

A Bayesian nonparametric procedure for comparing algorithms 1
A Convex Exemplar-based Approach to MAD-Bayes Dirichlet Process Mixture Models 3
A Convex Optimization Framework for Bi-Clustering 4
A Deeper Look at Planning as Learning from Replay 4
A Deterministic Analysis of Noisy Sparse Subspace Clustering for Dimensionality-reduced Data 2
A Divide and Conquer Framework for Distributed Graph Clustering 4
A Fast Variational Approach for Learning Markov Random Field Language Models 4
A General Analysis of the Convergence of ADMM 2
A Hybrid Approach for Probabilistic Inference using Random Projections 5
A Linear Dynamical System Model for Text 5
A Lower Bound for the Optimization of Finite Sums 0
A Modified Orthant-Wise Limited Memory Quasi-Newton Method with Convergence Analysis 4
A Multitask Point Process Predictive Model 3
A Nearly-Linear Time Framework for Graph-Structured Sparsity 1
A New Generalized Error Path Algorithm for Model Selection 4
A Probabilistic Model for Dirty Multi-task Feature Selection 4
A Provable Generalized Tensor Spectral Method for Uniform Hypergraph Partitioning 2
A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits 3
A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate 3
A Theoretical Analysis of Metric Hypothesis Transfer Learning 2
A Unified Framework for Outlier-Robust PCA-like Algorithms 3
A Unifying Framework of Anytime Sparse Gaussian Process Regression Models with Stochastic Variational Inference for Big Data 2
A low variance consistent test of relative dependency 4
A trust-region method for stochastic variational inference with applications to streaming data 4
Abstraction Selection in Model-based Reinforcement Learning 1
Accelerated Online Low Rank Tensor Learning for Multivariate Spatiotemporal Streams 5
Active Nearest Neighbors in Changing Environments 3
Adaptive Belief Propagation 3
Adaptive Stochastic Alternating Direction Method of Multipliers 4
Adding vs. Averaging in Distributed Primal-Dual Optimization 5
Algorithms for the Hard Pre-Image Problem of String Kernels and the General Problem of String Prediction 5
Alpha-Beta Divergences Discover Micro and Macro Structures in Data 5
An Aligned Subtree Kernel for Weighted Graphs 6
An Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization 3
An Empirical Exploration of Recurrent Network Architectures 3
An Empirical Study of Stochastic Variational Inference Algorithms for the Beta Bernoulli Process 4
An Explicit Sampling Dependent Spectral Error Bound for Column Subset Selection 1
An Online Learning Algorithm for Bilinear Models 4
An embarrassingly simple approach to zero-shot learning 4
Approval Voting and Incentives in Crowdsourcing 2
Approximate Dynamic Programming for Two-Player Zero-Sum Markov Games 2
Asymmetric Transfer Learning with Deep Gaussian Processes 4
Atomic Spatial Processes 3
Attribute Efficient Linear Regression with Distribution-Dependent Sampling 4
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift 3
Bayesian Multiple Target Localization 3
Bayesian and Empirical Bayesian Forests 4
BilBOWA: Fast Bilingual Distributed Representations without Word Alignments 4
Bimodal Modelling of Source Code and Natural Language 3
Binary Embedding: Fundamental Limits and Fast Algorithm 3
Bipartite Edge Prediction via Transductive Learning over Product Graphs 3
Blitz: A Principled Meta-Algorithm for Scaling Sparse Optimization 5
Boosted Categorical Restricted Boltzmann Machine for Computational Prediction of Splice Junctions 4
Budget Allocation Problem with Multiple Advertisers: A Game Theoretic View 5
CUR Algorithm for Partially Observed Matrices 3
Cascading Bandits: Learning to Rank in the Cascade Model 2
Causal Inference by Identification of Vector Autoregressive Processes with Hidden Components 3
Celeste: Variational inference for a generative model of astronomical images 2
Cheap Bandits 3
Classification with Low Rank and Missing Data 4
Community Detection Using Time-Dependent Personalized PageRank 4
Complete Dictionary Recovery Using Nonconvex Optimization 3
Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM 4
Compressing Neural Networks with the Hashing Trick 4
Consistent Multiclass Algorithms for Complex Performance Measures 3
Consistent estimation of dynamic and multi-layer block models 2
Context-based Unsupervised Data Fusion for Decision Making 3
Controversy in mechanistic modelling with Gaussian processes 2
Convergence rate of Bayesian tensor estimator and its minimax optimality 1
Convex Calibrated Surrogates for Hierarchical Classification 3
Convex Formulation for Learning from Positive and Unlabeled Data 3
Convex Learning of Multiple Tasks and their Structure 4
Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection 1
Coresets for Nonparametric Estimation - the Case of DP-Means 4
Correlation Clustering in Data Streams 1
Counterfactual Risk Minimization: Learning from Logged Bandit Feedback 4
DP-space: Bayesian Nonparametric Subspace Clustering with Small-variance Asymptotics 4
DRAW: A Recurrent Neural Network For Image Generation 3
Dealing with small data: On the generalization of context trees 3
Deep Edge-Aware Filters 4
Deep Learning with Limited Numerical Precision 3
Deep Unsupervised Learning using Nonequilibrium Thermodynamics 3
Deterministic Independent Component Analysis 2
DiSCO: Distributed Optimization for Self-Concordant Empirical Loss 4
Differentially Private Bayesian Optimization 1
Discovering Temporal Causal Relations from Subsampled Data 3
Distributed Box-Constrained Quadratic Optimization for Dual Linear SVM 7
Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower Bounds 2
Distributed Gaussian Processes 3
Distributed Inference for Dirichlet Process Mixture Models 4
Distributional Rank Aggregation, and an Axiomatic Analysis 1
Double Nyström Method: An Efficient and Accurate Nyström Scheme for Large-Scale Data Sets 5
Dynamic Sensing: Better Classification under Acquisition Constraints 2
Efficient Learning in Large-Scale Combinatorial Semi-Bandits 3
Efficient Training of LDA on a GPU by Mean-for-Mode Estimation 4
Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE) 5
Entropic Graph-based Posterior Regularization 2
Entropy evaluation based on confidence intervals of frequency estimates : Application to the learning of decision trees 4
Entropy-Based Concentration Inequalities for Dependent Variables 0
Exponential Integration for Hamiltonian Monte Carlo 4
Fast Kronecker Inference in Gaussian Processes with non-Gaussian Likelihoods 5
Faster Rates for the Frank-Wolfe Method over Strongly-Convex Sets 1
Faster cover trees 5
Feature-Budgeted Random Forest 4
Fictitious Self-Play in Extensive-Form Games 2
Finding Galaxies in the Shadows of Quasars with Gaussian Processes 2
Finding Linear Structure in Large Datasets with Scalable Canonical Correlation Analysis 3
Fixed-point algorithms for learning determinantal point processes 4
Following the Perturbed Leader for Online Structured Learning 2
From Word Embeddings To Document Distances 5
Functional Subspace Clustering with Application to Time Series 4
Gated Feedback Recurrent Neural Networks 3
Generalization error bounds for learning to rank: Does the length of document lists matter? 0
Generative Moment Matching Networks 5
Geometric Conditions for Subspace-Sparse Recovery 0
Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems 4
Gradient-based Hyperparameter Optimization through Reversible Learning 5
Guaranteed Tensor Decomposition: A Moment Approach 1
Harmonic Exponential Families on Manifolds 3
Hashing for Distributed Data 4
HawkesTopic: A Joint Model for Network Inference and Topic Modeling from Text-Based Cascades 2
Hidden Markov Anomaly Detection 3
High Confidence Policy Improvement 3
High Dimensional Bayesian Optimisation and Bandits via Additive Models 4
How Can Deep Rectifier Networks Achieve Linear Separability and Preserve Distances? 0
How Hard is Inference for Structured Prediction? 2
Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning 1
Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency Inputs 3
Inference in a Partially Observed Queuing Model with Applications in Ecology 1
Inferring Graphs from Cascades: A Sparse Recovery Framework 1
Information Geometry and Minimum Description Length Networks 5
Intersecting Faces: Non-negative Matrix Factorization With New Guarantees 2
Is Feature Selection Secure against Training Data Poisoning? 3
JUMP-Means: Small-Variance Asymptotics for Markov Jump Processes 2
K-hyperplane Hinge-Minimax Classifier 4
Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP) 3
Landmarking Manifolds with Gaussian Processes 4
Large-Scale Markov Decision Problems with KL Control Cost and its Application to Crowdsourcing 2
Large-scale Distributed Dependent Nonparametric Trees 4
Large-scale log-determinant computation through stochastic Chebyshev expansions 5
Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical Data 4
Latent Topic Networks: A Versatile Probabilistic Programming Framework for Topic Models 4
Learning Deep Structured Models 5
Learning Fast-Mixing Models for Structured Prediction 4
Learning Local Invariant Mahalanobis Distances 2
Learning Parametric-Output HMMs with Two Aliased States 2
Learning Program Embeddings to Propagate Feedback on Student Code 3
Learning Scale-Free Networks by Dynamic Node Specific Degree Prior 3
Learning Submodular Losses with the Lovasz Hinge 2
Learning Transferable Features with Deep Adaptation Networks 2
Learning Word Representations with Hierarchical Sparse Coding 4
Learning from Corrupted Binary Labels via Class-Probability Estimation 4
Learning to Search Better than Your Teacher 4
Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification 5
Long Short-Term Memory Over Recursive Structures 3
Low Rank Approximation using Error Correcting Coding Matrices 4
Low-Rank Matrix Recovery from Row-and-Column Affine Measurements 3
MADE: Masked Autoencoder for Distribution Estimation 6
MRA-based Statistical Learning from Incomplete Rankings 2
Manifold-valued Dirichlet Processes 3
Markov Chain Monte Carlo and Variational Inference: Bridging the Gap 4
Markov Mixed Membership Models 4
Message Passing for Collective Graphical Models 2
Metadata Dependent Mondrian Processes 4
Mind the duality gap: safer rules for the Lasso 3
Modeling Order in Neural Word Embeddings at Scale 4
Moderated and Drifting Linear Dynamical Systems 4
Multi-Task Learning for Subspace Segmentation 1
Multi-instance multi-label learning in the presence of novel class instances 3
Multi-view Sparse Co-clustering via Proximal Alternating Linearized Minimization 3
Multiview Triplet Embedding: Learning Attributes in Multiple Maps 5
Nested Sequential Monte Carlo Methods 4
Non-Gaussian Discriminative Factor Models via the Max-Margin Rank-Likelihood 4
Non-Linear Cross-Domain Collaborative Filtering via Hyper-Structure Transfer 3
Non-Stationary Approximate Modified Policy Iteration 2
Off-policy Model-based Learning under Unknown Factored Dynamics 3
On Deep Multi-View Representation Learning 5
On Greedy Maximization of Entropy 1
On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments 1
On Symmetric and Asymmetric LSHs for Inner Product Search 2
On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence 0
On the Optimality of Multi-Label Classification under Subset Zero-One Loss for Distributions Satisfying the Composition Property 4
On the Rate of Convergence and Error Bounds for LSTD(λ) 0
On the Relationship between Sum-Product Networks and Bayesian Networks 1
Online Learning of Eigenvectors 1
Online Time Series Prediction with Missing Data 1
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network 2
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays 4
Optimal and Adaptive Algorithms for Online Boosting 4
Optimizing Neural Networks with Kronecker-factored Approximate Curvature 4
Optimizing Non-decomposable Performance Measures: A Tale of Two Classes 4
Ordered Stick-Breaking Prior for Sequential MCMC Inference of Bayesian Nonparametric Models 5
Ordinal Mixed Membership Models 2
PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent 4
PU Learning for Matrix Completion 3
Paired-Dual Learning for Fast Training of Latent Variable Hinge-Loss MRFs 4
PeakSeg: constrained optimal segmentation and supervised penalty learning for peak detection in count data 4
Phrase-based Image Captioning 5
Predictive Entropy Search for Bayesian Optimization with Unknown Constraints 5
Preference Completion: Large-scale Collaborative Ranking from Pairwise Comparisons 4
Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo 3
Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks 4
Proteins, Particles, and Pseudo-Max-Marginals: A Submodular Approach 4
Pushing the Limits of Affine Rank Minimization by Adapting Probabilistic PCA 1
Qualitative Multi-Armed Bandits: A Quantile-Based Approach 2
Rademacher Observations, Private Data, and Boosting 4
Random Coordinate Descent Methods for Minimizing Decomposable Submodular Functions 2
Ranking from Stochastic Pairwise Preferences: Recovering Condorcet Winners and Tournament Solution Sets at the Top 2
Rebuilding Factorized Information Criterion: Asymptotically Accurate Marginal Likelihood 2
Reified Context Models 3
Removing systematic errors for exoplanet search via latent causes 4
Risk and Regret of Hierarchical Bayesian Learners 0
Robust Estimation of Transition Matrices in High Dimensional Heavy-tailed Vector Autoregressive Processes 2
Robust partially observable Markov decision process 2
Safe Exploration for Optimization with Gaussian Processes 3
Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret 3
Safe Screening for Multi-Task Feature Learning with Multiple Data Matrices 2
Safe Subspace Screening for Nuclear Norm Regularized Least Squares Problems 3
Scalable Bayesian Optimization Using Deep Neural Networks 5
Scalable Deep Poisson Factor Analysis for Topic Modeling 4
Scalable Model Selection for Large-Scale Factorial Relational Models 4
Scalable Nonparametric Bayesian Inference on Point Processes with Gaussian Processes 3
Scalable Variational Inference in Log-supermodular Models 3
Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix 3
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention 5
Simple regret for infinitely many armed bandits 2
Sparse Subspace Clustering with Missing Entries 2
Sparse Variational Inference for Generalized GP Models 3
Spectral Clustering via the Power Method - Provably 4
Spectral MLE: Top-K Rank Aggregation from Pairwise Comparisons 2
Statistical and Algorithmic Perspectives on Randomized Sketching for Ordinary Least-Squares 0
Stay on path: PCA along graph paths 1
Stochastic Dual Coordinate Ascent with Adaptive Probabilities 3
Stochastic Optimization with Importance Sampling for Regularized Loss Minimization 3
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization 3
Streaming Sparse Principal Component Analysis 4
Strongly Adaptive Online Learning 1
Structural Maxent Models 4
Submodularity in Data Subset Selection and Active Learning 4
Subsampling Methods for Persistent Homology 4
Support Matrix Machines 7
Surrogate Functions for Maximizing Precision at the Top 3
Swept Approximate Message Passing for Sparse Estimation 4
Telling cause from effect in deterministic linear dynamical systems 3
The Benefits of Learning with Strongly Convex Approximate Inference 1
The Composition Theorem for Differential Privacy 0
The Fundamental Incompatibility of Scalable Hamiltonian Monte Carlo and Naive Data Subsampling 1
The Hedge Algorithm on a Continuum 2
The Kendall and Mallows Kernels for Permutations 3
The Ladder: A Reliable Leaderboard for Machine Learning Competitions 4
The Power of Randomization: Distributed Submodular Maximization on Massive Datasets 2
Theory of Dual-sparse Regularized Randomized Reduction 2
Threshold Influence Model for Allocating Advertising Budgets 4
Towards a Learning Theory of Cause-Effect Inference 5
Towards a Lower Sample Complexity for Robust One-bit Compressed Sensing 2
Tracking Approximate Solutions of Parameterized Optimization Problems over Multi-Dimensional (Hyper-)Parameter Domains 3
Training Deep Convolutional Neural Networks to Play Go 4
Trust Region Policy Optimization 3
Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization 3
Universal Value Function Approximators 4
Unsupervised Domain Adaptation by Backpropagation 3
Unsupervised Learning of Video Representations using LSTMs 3
Unsupervised Riemannian Metric Learning for Histograms Using Aitchison Transformations 3
Variational Generative Stochastic Networks with Collaborative Shaping 5
Variational Inference for Gaussian Process Modulated Poisson Processes 1
Variational Inference with Normalizing Flows 3
Vector-Space Markov Random Fields via Exponential Families 2
Weight Uncertainty in Neural Network 4
Yinyang K-Means: A Drop-In Replacement of the Classic K-Means with Consistent Speedup 5
\ell_1,p-Norm Regularization: Error Bounds and Convergence Rate Analysis of First-Order Methods 2