NIPS 2016 Events with Videos
Invited Talks
Invited Talk (Breiman Lecture)s
Invited Talk (Posner Lecture)s
Orals
- Value Iteration Networks
- Graphons, mergeons, and so on!
- Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity
- Hierarchical Clustering via Spreading Metrics
- SDP Relaxation with Randomized Rounding for Energy Disaggregation
- Clustering with Same-Cluster Queries
- Bayesian Intermittent Demand Forecasting for Large Inventories
- Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA
- Synthesis of MCMC and Belief Propagation
- Fast and Provably Good Seedings for k-Means
- Deep Learning for Predicting Human Strategic Behavior
- Supervised learning through the lens of compression
- Using Fast Weights to Attend to the Recent Past
- MetaGrad: Multiple Learning Rates in Online Learning
- Sequential Neural Models with Stochastic Layers
- Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning
- Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
- Global Analysis of Expectation Maximization for Mixtures of Two Gaussians
- Matrix Completion has No Spurious Local Minimum
- Large-Scale Price Optimization via Network Flow
- Achieving the KS threshold in the general stochastic block model with linearized acyclic belief propagation
- Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
- Orthogonal Random Features
- Supervised Word Mover's Distance
- Poisson-Gamma dynamical systems
- Beyond Exchangeability: The Chinese Voting Process
- The Multiscale Laplacian Graph Kernel
- Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images
- Stochastic Online AUC Maximization
- Deep Learning without Poor Local Minima
- Without-Replacement Sampling for Stochastic Gradient Methods
- Regularized Nonlinear Acceleration
- Learning to Poke by Poking: Experiential Learning of Intuitive Physics
- Learning What and Where to Draw
- Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- Bayesian Optimization with Robust Bayesian Neural Networks
- Interpretable Distribution Features with Maximum Testing Power
- Showing versus doing: Teaching by demonstration
- Examples are not enough, learn to criticize! Criticism for Interpretability
- Relevant sparse codes with variational information bottleneck
- Dense Associative Memory for Pattern Recognition
Posters
- Improved Dropout for Shallow and Deep Learning
- Completely random measures for modelling block-structured sparse networks
- Stochastic Variational Deep Kernel Learning
- Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics
- Greedy Feature Construction
- DISCO Nets : DISsimilarity COefficients Networks
- Active Learning from Imperfect Labelers
- On Explore-Then-Commit strategies
- Adaptive Skills Adaptive Partitions (ASAP)
- Efficient High-Order Interaction-Aware Feature Selection Based on Conditional Mutual Information
- A Multi-Batch L-BFGS Method for Machine Learning
- Catching heuristics are optimal control policies
- A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order
- Consistent Kernel Mean Estimation for Functions of Random Variables
- Distributed Flexible Nonlinear Tensor Factorization
- Learning Parametric Sparse Models for Image Super-Resolution
- Kernel Observers: Systems-Theoretic Modeling and Inference of Spatiotemporally Evolving Processes
- Learning brain regions via large-scale online structured sparse dictionary learning
- A Bandit Framework for Strategic Regression
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- Sample Complexity of Automated Mechanism Design
- Deep Exploration via Bootstrapped DQN
- Search Improves Label for Active Learning
- CNNpack: Packing Convolutional Neural Networks in the Frequency Domain
- Edge-exchangeable graphs and sparsity
- Learning and Forecasting Opinion Dynamics in Social Networks
- Probing the Compositionality of Intuitive Functions
- Learning shape correspondence with anisotropic convolutional neural networks
- Data Programming: Creating Large Training Sets, Quickly
- An urn model for majority voting in classification ensembles
- Communication-Optimal Distributed Clustering
- Fairness in Learning: Classic and Contextual Bandits
- PAC-Bayesian Theory Meets Bayesian Inference
- On Robustness of Kernel Clustering
- A Bayesian method for reducing bias in neural representational similarity analysis
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Exponential Family Embeddings
- Combinatorial semi-bandit with known covariance
- k*-Nearest Neighbors: From Global to Local
- On Regularizing Rademacher Observation Losses
- Interaction Networks for Learning about Objects, Relations and Physics
- Binarized Neural Networks
- Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
- Composing graphical models with neural networks for structured representations and fast inference
- Algorithms and matching lower bounds for approximately-convex optimization
- Object based Scene Representations using Fisher Scores of Local Subspace Projections
- Unsupervised Learning for Physical Interaction through Video Prediction
- Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks
- Finding significant combinations of features in the presence of categorical covariates
- Sorting out typicality with the inverse moment matrix SOS polynomial
- Reconstructing Parameters of Spreading Models from Partial Observations
- Cooperative Inverse Reinforcement Learning
- Boosting with Abstention
- Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling
- Causal meets Submodular: Subset Selection with Directed Information
- Safe Exploration in Finite Markov Decision Processes with Gaussian Processes
- Dual Decomposed Learning with Factorwise Oracle for Structural SVM of Large Output Domain
- Multiple-Play Bandits in the Position-Based Model
- Computational and Statistical Tradeoffs in Learning to Rank
- Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences
- Learning User Perceived Clusters with Feature-Level Supervision
- Neural Universal Discrete Denoiser
- A primal-dual method for conic constrained distributed optimization problems
- Eliciting Categorical Data for Optimal Aggregation
- SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques
- Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images
- VIME: Variational Information Maximizing Exploration
- Semiparametric Differential Graph Models
- Sublinear Time Orthogonal Tensor Decomposition
- Achieving budget-optimality with adaptive schemes in crowdsourcing
- Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition
- Even Faster SVD Decomposition Yet Without Agonizing Pain
- Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles
- Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model
- Learning Additive Exponential Family Graphical Models via $\ell_{2,1}$-norm Regularized M-Estimation
- Residual Networks Behave Like Ensembles of Relatively Shallow Networks
- Full-Capacity Unitary Recurrent Neural Networks
- Quantum Perceptron Models
- Variational Information Maximization for Feature Selection
- A Minimax Approach to Supervised Learning
- Fast Distributed Submodular Cover: Public-Private Data Summarization
- Multimodal Residual Learning for Visual QA
- Optimizing affinity-based binary hashing using auxiliary coordinates
- Coresets for Scalable Bayesian Logistic Regression
- The Parallel Knowledge Gradient Method for Batch Bayesian Optimization
- Learning Multiagent Communication with Backpropagation
- Optimal Binary Classifier Aggregation for General Losses
- A Credit Assignment Compiler for Joint Prediction
- Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products
- Spatio-Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments
- Adaptive Concentration Inequalities for Sequential Decision Problems
- Cooperative Graphical Models
- Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition
- Efficient Second Order Online Learning by Sketching
- Learning Structured Sparsity in Deep Neural Networks
- Adversarial Multiclass Classification: A Risk Minimization Perspective
- Fast and Provably Good Seedings for k-Means
- Synthesis of MCMC and Belief Propagation
- Graphons, mergeons, and so on!
- Deep Learning for Predicting Human Strategic Behavior
- Tractable Operations for Arithmetic Circuits of Probabilistic Models
- Adaptive Maximization of Pointwise Submodular Functions With Budget Constraint
- A Locally Adaptive Normal Distribution
- Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm
- Contextual semibandits via supervised learning oracles
- Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering
- Dual Learning for Machine Translation
- Diffusion-Convolutional Neural Networks
- Convex Two-Layer Modeling with Latent Structure
- Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than $O(1/\epsilon)$
- Incremental Boosting Convolutional Neural Network for Facial Action Unit Recognition
- SURGE: Surface Regularized Geometry Estimation from a Single Image
- Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much
- Variational Bayes on Monte Carlo Steroids
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Can Peripheral Representations Improve Clutter Metrics on Complex Scenes?
- RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism
- Learnable Visual Markers
- Interpretable Nonlinear Dynamic Modeling of Neural Trajectories
- Stochastic Structured Prediction under Bandit Feedback
- On the Recursive Teaching Dimension of VC Classes
- f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
- Low-Rank Regression with Tensor Responses
- Double Thompson Sampling for Dueling Bandits
- Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters
- Dynamic matrix recovery from incomplete observations under an exact low-rank constraint
- Adaptive Averaging in Accelerated Descent Dynamics
- Bayesian Optimization for Probabilistic Programs
- Select-and-Sample for Spike-and-Slab Sparse Coding
- A Consistent Regularization Approach for Structured Prediction
- Learning Deep Embeddings with Histogram Loss
- Solving Marginal MAP Problems with NP Oracles and Parity Constraints
- Estimating the Size of a Large Network and its Communities from a Random Sample
- Deep ADMM-Net for Compressive Sensing MRI
- Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Learning Sparse Gaussian Graphical Models with Overlapping Blocks
- Professor Forcing: A New Algorithm for Training Recurrent Networks
- Pruning Random Forests for Prediction on a Budget
- Learning in Games: Robustness of Fast Convergence
- Data Poisoning Attacks on Factorization-Based Collaborative Filtering
- Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent
- Infinite Hidden Semi-Markov Modulated Interaction Point Process
- Linear Contextual Bandits with Knapsacks
- Deep Neural Networks with Inexact Matching for Person Re-Identification
- Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
- Deep Learning without Poor Local Minima
- Supervised Word Mover's Distance
- Interpretable Distribution Features with Maximum Testing Power
- Dense Associative Memory for Pattern Recognition
- Spectral Learning of Dynamic Systems from Nonequilibrium Data
- A Communication-Efficient Parallel Algorithm for Decision Tree
- Leveraging Sparsity for Efficient Submodular Data Summarization
- Large Margin Discriminant Dimensionality Reduction in Prediction Space
- Natural-Parameter Networks: A Class of Probabilistic Neural Networks
- A Probabilistic Programming Approach To Probabilistic Data Analysis
- Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
- An ensemble diversity approach to supervised binary hashing
- Tagger: Deep Unsupervised Perceptual Grouping
- A scaled Bregman theorem with applications
- Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation
- Exact Recovery of Hard Thresholding Pursuit
- New Liftable Classes for First-Order Probabilistic Inference
- Variational Inference in Mixed Probabilistic Submodular Models
- Unifying Count-Based Exploration and Intrinsic Motivation
- Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods
- Online Convex Optimization with Unconstrained Domains and Losses
- Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates
- Learning values across many orders of magnitude
- Single Pass PCA of Matrix Products
- Convolutional Neural Fabrics
- Optimal Black-Box Reductions Between Optimization Objectives
- A Sparse Interactive Model for Matrix Completion with Side Information
- Finite Sample Prediction and Recovery Bounds for Ordinal Embedding
- What Makes Objects Similar: A Unified Multi-Metric Learning Approach
- Cyclades: Conflict-free Asynchronous Machine Learning
- Disease Trajectory Maps
Symposiums
Tutorials
- Variational Inference: Foundations and Modern Methods
- Crowdsourcing: Beyond Label Generation
- Deep Reinforcement Learning Through Policy Optimization
- Theory and Algorithms for Forecasting Non-Stationary Time Series
- Generative Adversarial Networks
- ML Foundations and Methods for Precision Medicine and Healthcare
- Large-Scale Optimization: Beyond Stochastic Gradient Descent and Convexity
Workshops
- Nonconvex Optimization for Machine Learning: Theory and Practice
- Extreme Classification: Multi-class and Multi-label Learning in Extremely Large Label Spaces
- Brains and Bits: Neuroscience meets Machine Learning
- Bayesian Deep Learning
- Deep Learning for Action and Interaction
- Neural Abstract Machines & Program Induction
Report issues here.