NIPS 2015 Papers

Skip to yearly menu bar Skip to main content

Browse

mini compact topic detail

Alternating Minimization for Regression Problems with Vector-valued Outputs

Automatic Variational Inference in Stan

Inference for determinantal point processes without spectral knowledge

Interpolating Convex and Non-Convex Tensor Decompositions via the Subspace Norm

Fighting Bandits with a New Kind of Smoothness

Learning Bayesian Networks with Thousands of Variables

Fast Randomized Kernel Ridge Regression with Statistical Guarantees

Equilibrated adaptive learning rates for non-convex optimization

Bayesian dark knowledge

Enforcing balance allows local supervised learning in spiking recurrent networks

Matrix Completion with Noisy Side Information

Adaptive Online Learning

Pointer Networks

Tree-Guided MCMC Inference for Normalized Random Measure Mixture Models

Regressive Virtual Metric Learning

The Self-Normalized Estimator for Counterfactual Learning

A Market Framework for Eliciting Private Data

Sample Complexity of Learning Mahalanobis Distance Metrics

On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators

Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring

Fast Second Order Stochastic Backpropagation for Variational Inference

Approximating Sparse PCA from Incomplete Data

Cornering Stationary and Restless Mixing Bandits with Remix-UCB

Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization

Competitive Distribution Estimation: Why is Good-Turing Good

On the Global Linear Convergence of Frank-Wolfe Optimization Variants

Shepard Convolutional Neural Networks

Fast Convergence of Regularized Learning in Games

Principal Differences Analysis: Interpretable Characterization of Differences between Distributions

Bounding the Cost of Search-Based Lifted Inference

Precision-Recall-Gain Curves: PR Analysis Done Right

Frank-Wolfe Bayesian Quadrature: Probabilistic Integration with Theoretical Guarantees

Mixed Robust/Average Submodular Partitioning: Fast Algorithms, Guarantees, and Applications

Testing Closeness With Unequal Sized Samples

Sum-of-Squares Lower Bounds for Sparse PCA

Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)

A Reduced-Dimension fMRI Shared Response Model

On-the-Job Learning with Bayesian Decision Theory

Estimating Mixture Models via Mixtures of Polynomials

Optimal Testing for Properties of Distributions

Deep Convolutional Inverse Graphics Network

A class of network models recoverable by spectral clustering

Weighted Theta Functions and Embeddings with Applications to Max-Cut, Clustering and Summarization

Scalable Semi-Supervised Aggregation of Classifiers

Learning with Symmetric Label Noise: The Importance of Being Unhinged

Logarithmic Time Online Multiclass prediction

Efficient and Parsimonious Agnostic Active Learning

Collaborative Filtering with Graph Information: Consistency and Scalable Methods

Information-theoretic lower bounds for convex optimization with erroneous oracles

Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff

Accelerated Mirror Descent in Continuous and Discrete Time

Less is More: Nyström Computational Regularization

Multi-Layer Feature Reduction for Tree Structured Group Lasso via Hierarchical Projection

Market Scoring Rules Act As Opinion Pools For Risk-Averse Agents

Structured Transforms for Small-Footprint Deep Learning

Spherical Random Features for Polynomial Kernels

Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets

Backpropagation for Energy-Efficient Neuromorphic Computing

Attractor Network Dynamics Enable Preplay and Rapid Path Planning in Maze–like Environments

Learning Theory and Algorithms for Forecasting Non-stationary Time Series

Fast and Guaranteed Tensor Decomposition via Sketching

Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding

A Tractable Approximation to Optimal Point Process Filtering: Application to Neural Encoding

Empirical Localization of Homogeneous Divergences on Discrete Sample Spaces

Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets

Learning Wake-Sleep Recurrent Attention Models

Color Constancy by Learning to Predict Chromaticity from Luminance

Learning to Segment Object Candidates

The Return of the Gating Network: Combining Generative Models and Discriminative Training in Natural Image Priors

Action-Conditional Video Prediction using Deep Networks in Atari Games

Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation

NEXT: A System for Real-World Development, Evaluation, and Application of Active Learning

End-To-End Memory Networks

Deep Visual Analogy-Making

Attention-Based Models for Speech Recognition

Optimal Rates for Random Fourier Features

Top-k Multiclass SVM

Newton-Stein Method: A Second Order Method for GLMs via Stein's Lemma

Submodular Hamming Metrics

Extending Gossip Algorithms to Distributed Estimation of U-statistics

Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems

LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements

Sampling from Probabilistic Submodular Models

Where are they looking?

Super-Resolution Off the Grid

Spatial Transformer Networks

Training Very Deep Networks

Minimum Weight Perfect Matching via Blossom Belief Propagation

On the Pseudo-Dimension of Nearly Optimal Auctions

b-bit Marginal Regression

Closed-form Estimators for High-dimensional Generalized Linear Models

Measuring Sample Quality with Stein's Method

Randomized Block Krylov Methods for Stronger and Faster Approximate Singular Value Decomposition

Distributionally Robust Logistic Regression

Probabilistic Line Searches for Stochastic Optimization

Distributed Submodular Cover: Succinctly Summarizing Massive Data

On some provably correct cases of variational inference for topic models

Data Generation as Sequential Decision Making

Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width

Stochastic Expectation Propagation

The Human Kernel

Deep learning with Elastic Averaging SGD

Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels

High-dimensional neural spike train analysis with generalized count linear dynamical systems

Latent Bayesian melding for integrating individual and population models

Biologically Inspired Dynamic Textures for Probing Motion Perception

Linear Response Methods for Accurate Covariance Estimates from Mean Field Variational Bayes

Large-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings

Interactive Control of Diverse Complex Characters with Neural Networks

COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution

Efficient Learning of Continuous-Time Hidden Markov Models for Disease Progression

Semi-supervised Learning with Ladder Networks

Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Prediction

Gaussian Process Random Fields

Model-Based Relative Entropy Stochastic Search

Expectation Particle Belief Propagation

A Dual Augmented Block Minimization Framework for Learning with Limited Memory

Embedding Inference for Structured Multilabel Prediction

Gradient Estimation Using Stochastic Computation Graphs

Learning From Small Samples: An Analysis of Simple Decision Heuristics

A Universal Catalyst for First-Order Optimization

M-Statistic for Kernel Change-Point Detection

Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation

Copula variational inference

Kullback-Leibler Proximal Variational Inference

Sample Complexity Bounds for Iterative Stochastic Policy Optimization

Calibrated Structured Prediction

Semi-Supervised Factored Logistic Regression for High-Dimensional Neuroimaging Data

Decomposition Bounds for Marginal MAP

Lifted Inference Rules With Constraints

Learning Causal Graphs with Small Interventions

Learning Structured Output Representation using Deep Conditional Generative Models

From random walks to distances on unweighted graphs

Explore no more: Improved high-probability regret bounds for non-stochastic bandits

Fixed-Length Poisson MRF: Adding Dependencies to the Multinomial

Discrete Rényi Classifiers

Semi-Proximal Mirror-Prox for Nonsmooth Composite Minimization

Time-Sensitive Recommendation From Recurrent User Activities

BinaryConnect: Training Deep Neural Networks with binary weights during propagations

Skip-Thought Vectors

Principal Geodesic Analysis for Probability Measures under the Optimal Transport Metric

On Elicitation Complexity

Fast Lifted MAP Inference via Partitioning

Fast and Memory Optimal Low-Rank Matrix Approximation

Consistent Multilabel Classification

A Universal Primal-Dual Convex Optimization Framework

Rate-Agnostic (Causal) Structure Learning

Semi-supervised Sequence Learning

The Consistency of Common Neighbors for Link Prediction in Stochastic Blockmodels

The Poisson Gamma Belief Network

No-Regret Learning in Bayesian Games

Learnability of Influence in Networks

Convergence Analysis of Prediction Markets via Randomized Subspace Descent

Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions

Statistical Topological Data Analysis - A Kernel Perspective

Community Detection via Measure Space Embedding

Exploring Models and Data for Image Question Answering

Online Prediction at the Limit of Zero Temperature

Nearly Optimal Private LASSO

Convergence rates of sub-sampled Newton methods

A Complete Recipe for Stochastic Gradient MCMC

Efficient and Robust Automated Machine Learning

A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA

Structured Estimation with Atomic Norms: General Bounds and Applications

Subsampled Power Iteration: a Unified Algorithm for Block Models and Planted CSP's

A Recurrent Latent Variable Model for Sequential Data

Basis refinement strategies for linear value function approximation in MDPs

Learning with Relaxed Supervision

Preconditioned Spectral Descent for Deep Learning

Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices

Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning

Bayesian Optimization with Exponential Convergence

Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation

Softstar: Heuristic-Guided Probabilistic Inference

Reflection, Refraction, and Hamiltonian Monte Carlo

Grammar as a Foreign Language

Deep Poisson Factor Modeling

Winner-Take-All Autoencoders

Learning Continuous Control Policies by Stochastic Value Gradients

Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images

Estimating Jaccard Index with Missing Observations: A Matrix Calibration Approach

Local Causal Discovery of Direct Causes and Effects

Neural Adaptive Sequential Monte Carlo

Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms

Robust Spectral Inference for Joint Stochastic Matrix Factorization

A Bayesian Framework for Modeling Confidence in Perceptual Decision Making

Recognizing retinal ganglion cells in the dark

Associative Memory via a Sparse Recovery Model

Fast, Provable Algorithms for Isotonic Regression in all L_p-norms

Variational Dropout and the Local Reparameterization Trick

Adversarial Prediction Games for Multivariate Losses

Sparse and Low-Rank Tensor Decomposition

Path-SGD: Path-Normalized Optimization in Deep Neural Networks

Local Expectation Gradients for Black Box Variational Inference

Minimax Time Series Prediction

Deep Temporal Sigmoid Belief Networks for Sequence Modeling

Revenue Optimization against Strategic Buyers

Particle Gibbs for Infinite Hidden Markov Models

Sample Efficient Path Integral Control under Uncertainty

Robust Gaussian Graphical Modeling with the Trimmed Graphical Lasso

On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants

Spectral Representations for Convolutional Neural Networks

Differentially Private Learning of Structured Discrete Distributions

Learning structured densities via infinite dimensional exponential families

Learning spatiotemporal trajectories from manifold-valued longitudinal data

On the consistency theory of high dimensional variable screening

Online Gradient Boosting

StopWasting My Gradients: Practical SVRG

Generalization in Adaptive Data Analysis and Holdout Reuse

Spectral Norm Regularization of Orthonormal Representations for Graph Transduction

A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks

High Dimensional EM Algorithm: Statistical Optimization and Asymptotic Normality

A Theory of Decision Making Under Dynamic Context

Tractable Learning for Complex Probability Queries

Exactness of Approximate MAP Inference in Continuous MRFs

Sparse Linear Programming via Primal and Dual Augmented Coordinate Descent

Hidden Technical Debt in Machine Learning Systems

A Gaussian Process Model of Quasar Spectral Energy Distributions

Variance Reduced Stochastic Gradient Descent with Neighbors

Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction

Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradients

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question

Efficient Learning by Directed Acyclic Graph For Resource Constrained Prediction

Bayesian Active Model Selection with an Application to Automated Audiometry

Saliency, Scale and Information: Towards a Unifying Theory

An Active Learning Framework using Sparse-Graph Codes for Sparse Polynomials and Graph Sketching

Local Smoothness in Variance Reduced Optimization

Adaptive Primal-Dual Splitting Methods for Statistical Learning and Image Processing

Optimization Monte Carlo: Efficient and Embarrassingly Parallel Likelihood-Free Inference

Beyond Sub-Gaussian Measurements: High-Dimensional Structured Estimation with Sub-Exponential Designs

A Structural Smoothing Framework For Robust Graph Comparison

Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning

Combinatorial Bandits Revisited

Supervised Learning for Dynamical System Learning

Anytime Influence Bounds and the Explosive Behavior of Continuous-Time Diffusion Networks

Secure Multi-party Differential Privacy

Learning with a Wasserstein Loss

GP Kernels for Cross-Spectrum Analysis

Natural Neural Networks

A hybrid sampler for Poisson-Kingman mixture models

Fast Two-Sample Testing with Analytic Representations of Probability Measures

Robust PCA with compressed data

Regret-Based Pruning in Extensive-Form Games

Streaming Min-max Hypergraph Partitioning

Generative Image Modeling Using Spatial LSTMs

Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms

Visalogy: Answering Visual Analogy Questions

Matrix Completion Under Monotonic Single Index Models

Collaboratively Learning Preferences from Ordinal Data

Max-Margin Deep Generative Models

Learning to Transduce with Unbounded Memory

Inverse Reinforcement Learning with Locally Consistent Reward Functions

Efficient Non-greedy Optimization of Decision Trees

Probabilistic Curve Learning: Coulomb Repulsion and the Electrostatic Gaussian Process

Analysis of Robust PCA via Local Incoherence

On the Accuracy of Self-Normalized Log-Linear Models

Rectified Factor Networks

Infinite Factorial Dynamical Model

Is Approval Voting Optimal Given Approval Votes?

Segregated Graphs and Marginals of Chain Graph Models

Communication Complexity of Distributed Convex Learning and Optimization

Regularization Path of Cross-Validation Error Lower Bounds

When are Kalman-Filter Restless Bandits Indexable?

Subset Selection by Pareto Optimization

Adaptive Stochastic Optimization: From Sets to Paths

Policy Gradient for Coherent Risk Measures

Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach

MCMC for Variationally Sparse Gaussian Processes

End-to-end Learning of LDA by Mirror-Descent Back Propagation over a Deep Architecture

Regularized EM Algorithms: A Unified Framework and Statistical Guarantees

Learning with Incremental Iterative Regularization

Fast Rates for Exp-concave Empirical Risk Minimization

Beyond Convexity: Stochastic Quasi-Convex Optimization

Halting in Random Walk Kernels

Fast Bidirectional Probability Estimation in Markov Models

Optimal Linear Estimation under Unknown Nonlinear Transform

Max-Margin Majority Voting for Learning from Crowds

Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path

Variational Consensus Monte Carlo

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Learning with Group Invariant Features: A Kernel Perspective.

Probabilistic Variational Bounds for Graphical Models

Scalable Inference for Gaussian Process Models with Black-Box Likelihoods

Lifelong Learning with Non-i.i.d. Tasks

Asynchronous stochastic convex optimization: the noise is in the noise and SGD don't care

Teaching Machines to Read and Comprehend

Combinatorial Cascading Bandits

BACKSHIFT: Learning causal cyclic graphs from unknown shift interventions

Online Learning with Adversarial Delays

Cross-Domain Matching for Bag-of-Words Data via Kernel Embeddings of Latent Distributions

Practical and Optimal LSH for Angular Distance

Discriminative Robust Transformation Learning

Private Graphon Estimation for Sparse Graphs

SubmodBoxes: Near-Optimal Search for a Set of Diverse Object Proposals

Efficient Thompson Sampling for Online Matrix-Factorization Recommendation

Improved Iteration Complexity Bounds of Cyclic Block Coordinate Descent for Convex Problems

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

Matrix Completion from Fewer Entries: Spectral Detectability and Rank Estimation

The Population Posterior and Bayesian Modeling on Streams

Learning to Linearize Under Uncertainty

Fast Classification Rates for High-dimensional Gaussian Generative Models

Lifted Symmetry Detection and Breaking for MAP Inference

Evaluating the statistical significance of biclusters

Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis

Bandits with Unobserved Confounders: A Causal Approach

Online Learning with Gaussian Payoffs and Side Observations

Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models

Efficient Output Kernel Learning for Multiple Tasks

Human Memory Search as Initial-Visit Emitting Random Walk

Finite-Time Analysis of Projected Langevin Monte Carlo

Unified View of Matrix Completion under General Structural Constraints

Non-convex Statistical Optimization for Sparse Tensor Graphical Model

Fast Distributed k-Center Clustering with Outliers on Massive Data

Learning both Weights and Connections for Efficient Neural Network

The Brain Uses Reliability of Stimulus Information when Making Perceptual Decisions

Convergence Rates of Active Learning for Maximum Likelihood Estimation

On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs

SGD Algorithms based on Incomplete U-statistics: Large-Scale Minimization of Empirical Risk

Unsupervised Learning by Program Synthesis

Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets

Predtron: A Family of Online Algorithms for General Prediction Problems

Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families

Differentially private subspace clustering

Linear Multi-Resource Allocation with Semi-Bandit Feedback

Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling

Matrix Manifold Optimization for Gaussian Mixtures

Subspace Clustering with Irrelevant Features via Robust Dantzig Selector

Large-scale probabilistic predictors with and without guarantees of validity

Hessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks

Parallel Recursive Best-First AND/OR Search for Exact MAP Inference in Graphical Models

A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure

Convolutional Neural Networks with Intra-Layer Recurrent Connections for Scene Labeling

A Generalization of Submodular Cover via the Diminishing Return Property on the Integer Lattice

Sparse PCA via Bipartite Matchings

Statistical Model Criticism using Kernel Two Sample Tests

Recovering Communities in the General Stochastic Block Model Without Knowing the Parameters

Active Learning from Weak and Strong Labelers

Monotone k-Submodular Function Maximization with Size Constraints

Bidirectional Recurrent Neural Networks as Generative Models

Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy

Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

Convolutional spike-triggered covariance analysis for neural subunit models

Efficient Compressive Phase Retrieval with Constrained Sensing Vectors

Robust Feature-Sample Linear Discriminant Analysis for Brain Disorders Diagnosis

Learning Large-Scale Poisson DAG Models based on OverDispersion Scoring

Black-box optimization of noisy functions with unknown smoothness

Tractable Bayesian Network Structure Learning with Bounded Vertex Cover Number

Robust Regression via Hard Thresholding

Barrier Frank-Wolfe for Marginal Inference

Online Learning for Adversaries with Memory: Price of Past Mistakes

Sparse Local Embeddings for Extreme Multi-label Classification

Compressive spectral embedding: sidestepping the SVD

Character-level Convolutional Networks for Text Classification

GAP Safe screening rules for sparse multi-task and multi-class models

Online Rank Elicitation for Plackett-Luce: A Dueling Bandits Approach

Online F-Measure Optimization

Rethinking LDA: Moment Matching for Discrete ICA

On the Optimality of Classifier Chain for Multi-label Classification

Column Selection via Adaptive Sampling

Spectral Learning of Large Structured HMMs for Comparative Epigenomics

Nonparametric von Mises Estimators for Entropies, Divergences and Mutual Informations

M-Best-Diverse Labelings for Submodular Energies and Beyond

A Nonconvex Optimization Framework for Low Rank Matrix Estimation

Parallelizing MCMC with Random Partition Trees

Accelerated Proximal Gradient Methods for Nonconvex Programming

Individual Planning in Infinite-Horizon Multiagent Settings: Inference, Structure and Scalability

Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits

Synaptic Sampling: A Bayesian Approach to Neural Network Plasticity and Rewiring

Orthogonal NMF through Subspace Exploration

Stochastic Online Greedy Learning with Semi-bandit Feedbacks

Deep Knowledge Tracing

Copeland Dueling Bandits

Learning visual biases from human imagination

Tensorizing Neural Networks

3D Object Proposals for Accurate Object Class Detection

Bounding errors of Expectation-Propagation

Policy Evaluation Using the Ω-Return

Deeply Learning the Messages in Message Passing Inference

HONOR: Hybrid Optimization for NOn-convex Regularized problems

A fast, universal algorithm to learn parametric nonlinear embeddings

Smooth and Strong: MAP Inference with Linear Convergence

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

The Pareto Regret Frontier for Bandits

Streaming, Distributed Variational Inference for Bayesian Nonparametrics

Optimal Ridge Detection using Coverage Risk

Texture Synthesis Using Convolutional Neural Networks

Smooth Interactive Submodular Set Cover

Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing

Algorithmic Stability and Uniform Generalization

Space-Time Local Embeddings

A Convergent Gradient Descent Algorithm for Rank Minimization and Semidefinite Programming from Random Linear Measurements

On the Limitation of Spectral Methods: From the Gaussian Hidden Clique Problem to Rank-One Perturbations of Gaussian Tensors

Robust Portfolio Optimization

Expressing an Image Stream with a Sequence of Natural Sentences

Fast and Accurate Inference of Plackett–Luce Models

Unlocking neural population non-stationarities using hierarchical dynamics models

Parallel Correlation Clustering on Big Graphs

Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning

Planar Ultrametrics for Image Segmentation

Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling

Adaptive Low-Complexity Sequential Inference for Dirichlet Process Mixture Models

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks