icml 2015 论文列表Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015. |
A New Generalized Error Path Algorithm for Model Selection.
Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization.
On the Optimality of Multi-Label Classification under Subset Zero-One Loss for Distributions Satisfying the Composition Property.
Deterministic Independent Component Analysis.
Inference in a Partially Observed Queuing Model with Applications in Ecology.
A trust-region method for stochastic variational inference with applications to streaming data.
Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo.
Boosted Categorical Restricted Boltzmann Machine for Computational Prediction of Splice Junctions.
Moderated and Drifting Linear Dynamical Systems.
Sparse Subspace Clustering with Missing Entries.
An Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization.
PU Learning for Matrix Completion.
Entropy-Based Concentration Inequalities for Dependent Variables.
Multi-instance multi-label learning in the presence of novel class instances.
A Convex Exemplar-based Approach to MAD-Bayes Dirichlet Process Mixture Models.
Optimizing Neural Networks with Kronecker-factored Approximate Curvature.
Consistent Multiclass Algorithms for Complex Performance Measures.
Fixed-point algorithms for learning determinantal point processes.
High Confidence Policy Improvement.
PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent.
Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret.
Complete Dictionary Recovery Using Nonconvex Optimization.
An Empirical Exploration of Recurrent Network Architectures.
Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems.
Optimal and Adaptive Algorithms for Online Boosting.
A Deeper Look at Planning as Learning from Replay.
Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix.
Intersecting Faces: Non-negative Matrix Factorization With New Guarantees.
Compressing Neural Networks with the Hashing Trick.
Distributed Inference for Dirichlet Process Mixture Models.
Modeling Order in Neural Word Embeddings at Scale.
Deep Unsupervised Learning using Nonequilibrium Thermodynamics.
Learning Scale-Free Networks by Dynamic Node Specific Degree Prior.
Correlation Clustering in Data Streams.
Scalable Nonparametric Bayesian Inference on Point Processes with Gaussian Processes.
Removing systematic errors for exoplanet search via latent causes.
Bernhard Schölkopf David W. Hogg Dun Wang Daniel Foreman-Mackey Dominik Janzing Carl-Johann Simon-Gabriel Jonas Peters
A Fast Variational Approach for Learning Markov Random Field Language Models.
Proteins, Particles, and Pseudo-Max-Marginals: A Submodular Approach.
Online Time Series Prediction with Missing Data.
How Hard is Inference for Structured Prediction?
Scalable Bayesian Optimization Using Deep Neural Networks.
Jasper Snoek Oren Rippel Kevin Swersky Ryan Kiros Nadathur Satish Narayanan Sundaram Md. Mostofa Ali Patwary Prabhat Ryan P. Adams
Binary Embedding: Fundamental Limits and Fast Algorithm.
An embarrassingly simple approach to zero-shot learning.
Subsampling Methods for Persistent Homology.
Cheap Bandits.
Bimodal Modelling of Source Code and Natural Language.
Gradient-based Hyperparameter Optimization through Reversible Learning.
Distributional Rank Aggregation, and an Axiomatic Analysis.
Celeste: Variational inference for a generative model of astronomical images.
Jeffrey Regier Andrew C. Miller Jon McAuliffe Ryan P. Adams Matthew D. Hoffman Dustin Lang David Schlegel Prabhat
Phrase-based Image Captioning.
Context-based Unsupervised Data Fusion for Decision Making.
Gated Feedback Recurrent Neural Networks.
Learning to Search Better than Your Teacher.
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.
Kelvin Xu Jimmy Ba Ryan Kiros Kyunghyun Cho Aaron C. Courville Ruslan Salakhutdinov Richard S. Zemel Yoshua Bengio
A Hybrid Approach for Probabilistic Inference using Random Projections.
A Multitask Point Process Predictive Model.
Algorithms for the Hard Pre-Image Problem of String Kernels and the General Problem of String Prediction.
Low-Rank Matrix Recovery from Row-and-Column Affine Measurements.
Unsupervised Riemannian Metric Learning for Histograms Using Aitchison Transformations.
Entropic Graph-based Posterior Regularization.
Feature-Budgeted Random Forest.
Adding vs. Averaging in Distributed Primal-Dual Optimization.
Variational Generative Stochastic Networks with Collaborative Shaping.
Submodularity in Data Subset Selection and Active Learning.
Bayesian Multiple Target Localization.
The Kendall and Mallows Kernels for Permutations.
On Symmetric and Asymmetric LSHs for Inner Product Search.
Causal Inference by Identification of Vector Autoregressive Processes with Hidden Components.
Preference Completion: Large-scale Collaborative Ranking from Pairwise Comparisons.
Discovering Temporal Causal Relations from Subsampled Data.
Trust Region Policy Optimization.
Bipartite Edge Prediction via Transductive Learning over Product Graphs.
Active Nearest Neighbors in Changing Environments.
Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks.
Convex Calibrated Surrogates for Hierarchical Classification.
Robust Estimation of Transition Matrices in High Dimensional Heavy-tailed Vector Autoregressive Processes.
Hidden Markov Anomaly Detection.
Scalable Deep Poisson Factor Analysis for Topic Modeling.
Variational Inference for Gaussian Process Modulated Poisson Processes.
Scalable Variational Inference in Log-supermodular Models.
Community Detection Using Time-Dependent Personalized PageRank.
Learning Deep Structured Models.
Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP).
Training Deep Convolutional Neural Networks to Play Go.
Harmonic Exponential Families on Manifolds.
Safe Screening for Multi-Task Feature Learning with Multiple Data Matrices.
Deep Learning with Limited Numerical Precision.
Stay on path: PCA along graph paths.
Generative Moment Matching Networks.
A Theoretical Analysis of Metric Hypothesis Transfer Learning.
Predictive Entropy Search for Bayesian Optimization with Unknown Constraints.
Is Feature Selection Secure against Training Data Poisoning?
A Convex Optimization Framework for Bi-Clustering.
Deep Edge-Aware Filters.
Qualitative Multi-Armed Bandits: A Quantile-Based Approach.
Large-scale Distributed Dependent Nonparametric Trees.
Hashing for Distributed Data.
Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection.
Learning Submodular Losses with the Lovasz Hinge.
Weight Uncertainty in Neural Network.
Long Short-Term Memory Over Recursive Structures.
An Empirical Study of Stochastic Variational Inference Algorithms for the Beta Bernoulli Process.
Geometric Conditions for Subspace-Sparse Recovery.
Entropy evaluation based on confidence intervals of frequency estimates : Application to the learning of decision trees.
Non-Stationary Approximate Modified Policy Iteration.
K-hyperplane Hinge-Minimax Classifier.
Convex Learning of Multiple Tasks and their Structure.
Controversy in mechanistic modelling with Gaussian processes.
Variational Inference with Normalizing Flows.
On the Rate of Convergence and Error Bounds for LSTD(\(\lambda\)).
Consistent estimation of dynamic and multi-layer block models.
\(\ell_{1, p}\)-Norm Regularization: Error Bounds and Convergence Rate Analysis of First-Order Methods.
Guaranteed Tensor Decomposition: A Moment Approach.
Distributed Gaussian Processes.
Multiview Triplet Embedding: Learning Attributes in Multiple Maps.
DRAW: A Recurrent Neural Network For Image Generation.
Towards a Learning Theory of Cause-Effect Inference.
Risk and Regret of Hierarchical Bayesian Learners.
MRA-based Statistical Learning from Incomplete Rankings.
A Deterministic Analysis of Noisy Sparse Subspace Clustering for Dimensionality-reduced Data.
CUR Algorithm for Partially Observed Matrices.
Strongly Adaptive Online Learning.
Threshold Influence Model for Allocating Advertising Budgets.
Convex Formulation for Learning from Positive and Unlabeled Data.
The Composition Theorem for Differential Privacy.
Double Nyström Method: An Efficient and Accurate Nyström Scheme for Large-Scale Data Sets.
Rebuilding Factorized Information Criterion: Asymptotically Accurate Marginal Likelihood.
Complex Event Detection using Semantic Saliency and Nearly-Isotonic SVM.
Metadata Dependent Mondrian Processes.
On Greedy Maximization of Entropy.
Approximate Dynamic Programming for Two-Player Zero-Sum Markov Games.
Universal Value Function Approximators.
Sparse Variational Inference for Generalized GP Models.
Nested Sequential Monte Carlo Methods.
On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments.
Convergence rate of Bayesian tensor estimator and its minimax optimality.
A Bayesian nonparametric procedure for comparing algorithms.
Non-Gaussian Discriminative Factor Models via the Max-Margin Rank-Likelihood.
Dealing with small data: On the generalization of context trees.
The Power of Randomization: Distributed Submodular Maximization on Massive Datasets.
Scalable Model Selection for Large-Scale Factorial Relational Models.
Markov Chain Monte Carlo and Variational Inference: Bridging the Gap.
Multi-Task Learning for Subspace Segmentation.
Manifold-valued Dirichlet Processes.
Non-Linear Cross-Domain Collaborative Filtering via Hyper-Structure Transfer.
Unsupervised Domain Adaptation by Backpropagation.
Blitz: A Principled Meta-Algorithm for Scaling Sparse Optimization.
Faster cover trees.
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays.
Exponential Integration for Hamiltonian Monte Carlo.
Simple regret for infinitely many armed bandits.
Swept Approximate Message Passing for Sparse Estimation.
Efficient Learning in Large-Scale Combinatorial Semi-Bandits.
Safe Subspace Screening for Nuclear Norm Regularized Least Squares Problems.
Learning Program Embeddings to Propagate Feedback on Student Code.
On Deep Multi-View Representation Learning.
A Probabilistic Model for Dirty Multi-task Feature Selection.
Learning Fast-Mixing Models for Structured Prediction.
Large-Scale Markov Decision Problems with KL Control Cost and its Application to Crowdsourcing.
Reified Context Models.
Following the Perturbed Leader for Online Structured Learning.
Finding Galaxies in the Shadows of Quasars with Gaussian Processes.
Enabling scalable stochastic gradient-based inference for Gaussian processes by employing the Unbiased LInear System SolvEr (ULISSE).
The Ladder: A Reliable Leaderboard for Machine Learning Competitions.
Safe Exploration for Optimization with Gaussian Processes.
Distributed Box-Constrained Quadratic Optimization for Dual Linear SVM.
Inferring Graphs from Cascades: A Sparse Recovery Framework.
Bayesian and Empirical Bayesian Forests.
From Word Embeddings To Document Distances.
Rademacher Observations, Private Data, and Boosting.
Support Matrix Machines.
A Nearly-Linear Time Framework for Graph-Structured Sparsity.
Differentially Private Bayesian Optimization.
Large-scale log-determinant computation through stochastic Chebyshev expansions.
Adaptive Belief Propagation.
An Online Learning Algorithm for Bilinear Models.
MADE: Masked Autoencoder for Distribution Estimation.
HawkesTopic: A Joint Model for Network Inference and Topic Modeling from Text-Based Cascades.
DP-space: Bayesian Nonparametric Subspace Clustering with Small-variance Asymptotics.
Message Passing for Collective Graphical Models.
Unsupervised Learning of Video Representations using LSTMs.
A Linear Dynamical System Model for Text.
The Hedge Algorithm on a Continuum.
Counterfactual Risk Minimization: Learning from Logged Bandit Feedback.
Fictitious Self-Play in Extensive-Form Games.
Alpha-Beta Divergences Discover Micro and Macro Structures in Data.
Random Coordinate Descent Methods for Minimizing Decomposable Submodular Functions.
Latent Topic Networks: A Versatile Probabilistic Programming Framework for Topic Models.
Cascading Bandits: Learning to Rank in the Cascade Model.
Multi-view Sparse Co-clustering via Proximal Alternating Linearized Minimization.
BilBOWA: Fast Bilingual Distributed Representations without Word Alignments.
Towards a Lower Sample Complexity for Robust One-bit Compressed Sensing.
Asymmetric Transfer Learning with Deep Gaussian Processes.
Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification.
Off-policy Model-based Learning under Unknown Factored Dynamics.
Low Rank Approximation using Error Correcting Coding Matrices.
JUMP-Means: Small-Variance Asymptotics for Markov Jump Processes.
Vector-Space Markov Random Fields via Exponential Families.
Stochastic Dual Coordinate Ascent with Adaptive Probabilities.
Ranking from Stochastic Pairwise Preferences: Recovering Condorcet Winners and Tournament Solution Sets at the Top.
Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency Inputs.
Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical Data.
Learning Parametric-Output HMMs with Two Aliased States.
On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence.
Statistical and Algorithmic Perspectives on Randomized Sketching for Ordinary Least-Squares.
Fast Kronecker Inference in Gaussian Processes with non-Gaussian Likelihoods.
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network.
Ordinal Mixed Membership Models.
Yinyang K-Means: A Drop-In Replacement of the Classic K-Means with Consistent Speedup.
A Unifying Framework of Anytime Sparse Gaussian Process Regression Models with Stochastic Variational Inference for Big Data.
Online Learning of Eigenvectors.
Ordered Stick-Breaking Prior for Sequential MCMC Inference of Bayesian Nonparametric Models.
Faster Rates for the Frank-Wolfe Method over Strongly-Convex Sets.
The Fundamental Incompatibility of Scalable Hamiltonian Monte Carlo and Naive Data Subsampling.
Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning.
How Can Deep Rectifier Networks Achieve Linear Separability and Preserve Distances?
A Divide and Conquer Framework for Distributed Graph Clustering.
Streaming Sparse Principal Component Analysis.
A Unified Framework for Outlier-Robust PCA-like Algorithms.
Markov Mixed Membership Models.
Landmarking Manifolds with Gaussian Processes.
Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower Bounds.
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.
Tracking Approximate Solutions of Parameterized Optimization Problems over Multi-Dimensional (Hyper-)Parameter Domains.
Budget Allocation Problem with Multiple Advertisers: A Game Theoretic View.
Pushing the Limits of Affine Rank Minimization by Adapting Probabilistic PCA.
The Benefits of Learning with Strongly Convex Approximate Inference.
A Provable Generalized Tensor Spectral Method for Uniform Hypergraph Partitioning.
Structural Maxent Models.
Paired-Dual Learning for Fast Training of Latent Variable Hinge-Loss MRFs.
Spectral MLE: Top-K Rank Aggregation from Pairwise Comparisons.
DiSCO: Distributed Optimization for Self-Concordant Empirical Loss.
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization.
A General Analysis of the Convergence of ADMM.
Mind the duality gap: safer rules for the Lasso.
PeakSeg: constrained optimal segmentation and supervised penalty learning for peak detection in count data.
Generalization error bounds for learning to rank: Does the length of document lists matter?
Theory of Dual-sparse Regularized Randomized Reduction.
High Dimensional Bayesian Optimisation and Bandits via Additive Models.
Telling cause from effect in deterministic linear dynamical systems.
A Modified Orthant-Wise Limited Memory Quasi-Newton Method with Convergence Analysis.
Dynamic Sensing: Better Classification under Acquisition Constraints.
Classification with Low Rank and Missing Data.
Atomic Spatial Processes.
Accelerated Online Low Rank Tensor Learning for Multivariate Spatiotemporal Streams.
Functional Subspace Clustering with Application to Time Series.
A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits.
Coresets for Nonparametric Estimation - the Case of DP-Means.
Optimizing Non-decomposable Performance Measures: A Tale of Two Classes.
Surrogate Functions for Maximizing Precision at the Top.
Abstraction Selection in Model-based Reinforcement Learning.
Finding Linear Structure in Large Datasets with Scalable Canonical Correlation Analysis.
Learning Local Invariant Mahalanobis Distances.
Attribute Efficient Linear Regression with Distribution-Dependent Sampling.
A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate.
An Explicit Sampling Dependent Spectral Error Bound for Column Subset Selection.
Learning from Corrupted Binary Labels via Class-Probability Estimation.
On the Relationship between Sum-Product Networks and Bayesian Networks.
Robust partially observable Markov decision process.
Learning Transferable Features with Deep Adaptation Networks.
Learning Word Representations with Hierarchical Sparse Coding.
A Lower Bound for the Optimization of Finite Sums.
Adaptive Stochastic Alternating Direction Method of Multipliers.
Efficient Training of LDA on a GPU by Mean-for-Mode Estimation.
Information Geometry and Minimum Description Length Networks.
Spectral Clustering via the Power Method - Provably.
An Aligned Subtree Kernel for Weighted Graphs.
A low variance consistent test of relative dependency.
Approval Voting and Incentives in Crowdsourcing.
Stochastic Optimization with Importance Sampling for Regularized Loss Minimization.