Downloads 2016
Number of events: 659
- 3D Deep Learning
- A Bandit Framework for Strategic Regression
- A Bayesian method for reducing bias in neural representational similarity analysis
- A Bio-inspired Redundant Sensing Architecture
- Accelerating Stochastic Composition Optimization
- Achieving budget-optimality with adaptive schemes in crowdsourcing
- Achieving the KS threshold in the general stochastic block model with linearized acyclic belief propagation
- A Communication-Efficient Parallel Algorithm for Decision Tree
- A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order
- A Consistent Regularization Approach for Structured Prediction
- A Constant-Factor Bi-Criteria Approximation Guarantee for k-means++
- A Credit Assignment Compiler for Joint Prediction
- Active Learning from Imperfect Labelers
- Active Learning with Oracle Epiphany
- Active Nearest-Neighbor Learning in Metric Spaces
- Adapting Microsoft's CNTK and ResNet-18 to Enable Strong-Scaling on Cray Systems
- Adaptive and Scalable Nonparametric Methods in Machine Learning
- Adaptive Averaging in Accelerated Descent Dynamics
- Adaptive Concentration Inequalities for Sequential Decision Problems
- Adaptive Data Analysis
- Adaptive Maximization of Pointwise Submodular Functions With Budget Constraint
- Adaptive Neural Compilation
- Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy
- Adaptive optimal training of animal behavior
- Adaptive Skills Adaptive Partitions (ASAP)
- Adaptive Smoothed Online Multi-Task Learning
- Advances in Approximate Bayesian Inference
- Adventures with Deep Generator Networks
- Adversarial Multiclass Classification: A Risk Minimization Perspective
- Adversarial Training
- A forward model at Purkinje cell synapses facilitates cerebellar anticipatory control
- Agnostic Estimation for Misspecified Phase Retrieval Models
- Algorithms and matching lower bounds for approximately-convex optimization
- A Locally Adaptive Normal Distribution
- A Minimax Approach to Supervised Learning
- A Multi-Batch L-BFGS Method for Machine Learning
- A Multi-step Inertial Forward-Backward Splitting Method for Non-convex Optimization
- An algorithm for L1 nearest neighbor search via monotonic embedding
- An Architecture for Deep, Hierarchical Generative Models
- Ancestral Causal Inference
- Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm
- An Efficient Streaming Algorithm for the Submodular Cover Problem
- An ensemble diversity approach to supervised binary hashing
- An equivalence between high dimensional Bayes optimal inference and M-estimation
- A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing
- A Non-generative Framework and Convex Relaxations for Unsupervised Learning
- An Online Sequence-to-Sequence Model Using Partial Conditioning
- A Non-parametric Learning Method for Confidently Estimating Patient's Clinical State and Dynamics
- An urn model for majority voting in classification ensembles
- A posteriori error bounds for joint matrix decomposition problems
- A Powerful Generative Model Using Random Weights for the Deep Image Representation
- Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods
- A primal-dual method for conic constrained distributed optimization problems
- A Probabilistic Framework for Deep Learning
- A Probabilistic Model of Social Decision Making based on Reward Maximization
- A Probabilistic Programming Approach To Probabilistic Data Analysis
- A Pseudo-Bayesian Algorithm for Robust PCA
- Architectural Complexity Measures of Recurrent Neural Networks
- A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
- A scaled Bregman theorem with applications
- A Simple Practical Accelerated Method for Finite Sums
- A Sparse Interactive Model for Matrix Completion with Side Information
- Assortment Optimization Under the Mallows model
- A state-space model of cross-region dynamic connectivity in MEG/EEG
- A state-space model of cross-region dynamic connectivity in MEG/EEG
- Asynchronous Parallel Greedy Coordinate Descent
- A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
- Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
- A Unified Approach for Learning the Parameters of Sum-Product Networks
- Automated scalable segmentation of neurons from multispectral images
- Automated simulation and replication of fMRI experiments
- Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks
- Autonomous exploration, active learning and human guidance with open-source Poppy humanoid robot platform and Explauto library
- Average-case hardness of RIP certification
- Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction
- Backprop KF: Learning Discriminative Deterministic State Estimators
- Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition
- Barzilai-Borwein Step Size for Stochastic Gradient Descent
- Batched Gaussian Process Bandit Optimization via Determinantal Point Processes
- Bayesian Deep Learning
- Bayesian Intermittent Demand Forecasting for Large Inventories
- Bayesian latent structure discovery from multi-neuron recordings
- Bayesian Optimization: Black-box Optimization and Beyond
- Bayesian optimization for automated model selection
- Bayesian Optimization for Probabilistic Programs
- Bayesian optimization under mixed constraints with a slack-variable augmented Lagrangian
- Bayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach
- Bayesian Optimization with Robust Bayesian Neural Networks
- beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data
- Beyond Exchangeability: The Chinese Voting Process
- Binarized Neural Networks
- Bi-Objective Online Matching and Submodular Allocations
- Biometric applications of CNNs: get a job at "Impending Technologies"!
- Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning
- Blind Attacks on Machine Learners
- Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering
- Boosting with Abstention
- Bootstrap Model Aggregation for Distributed Statistical Learning
- Brain-machine interface spelling device based on reinforcement learning
- Brains and Bits: Neuroscience meets Machine Learning
- Brains and Bits: Neuroscience meets Machine Learning (2nd day)
- Brains on Beats
- Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation
- Budgeted stream-based active learning via adaptive submodular maximization
- Can Active Memory Replace Attention?
- Can Peripheral Representations Improve Clutter Metrics on Complex Scenes?
- Catching heuristics are optimal control policies
- Causal Bandits: Learning Good Interventions via Causal Inference
- Causal meets Submodular: Subset Selection with Directed Information
- Challenges in Machine Learning: Gaming and Education
- CliqueCNN: Deep Unsupervised Exemplar Learning
- Clustering Signed Networks with the Geometric Mean of Laplacians
- Clustering with Bregman Divergences: an Asymptotic Analysis
- Clustering with Same-Cluster Queries
- CMA-ES with Optimal Covariance Update and Storage Complexity
- CNNpack: Packing Convolutional Neural Networks in the Frequency Domain
- Coevolutionary Latent Feature Processes for Continuous-Time User-Item Interactions
- Cognitive Computation: Integrating Neural and Symbolic Approaches
- Coin Betting and Parameter-Free Online Learning
- Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks
- Combinatorial Energy Learning for Image Segmentation
- Combinatorial Multi-Armed Bandit with General Reward Functions
- Combinatorial semi-bandit with known covariance
- Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning
- Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
- Combining Low-Density Separators with CNNs
- Communication-Optimal Distributed Clustering
- Community Detection on Evolving Graphs
- Completely random measures for modelling block-structured sparse networks
- Composing graphical models with neural networks for structured representations and fast inference
- Computational and Statistical Tradeoffs in Learning to Rank
- Computing and maximizing influence in linear threshold and triggering models
- Computing with Spikes
- Conditional Generative Moment-Matching Networks
- Conditional Image Generation with PixelCNN Decoders
- Confusions over Time: An Interpretable Bayesian Model to Characterize Trends in Decision Making
- “Congruent” and “Opposite” Neurons: Sisters for Multisensory Integration and Segregation
- Connectomics II: Opportunities and Challenges for Machine Learning
- Consistent Estimation of Functions of Data Missing Non-Monotonically and Not at Random
- Consistent Kernel Mean Estimation for Functions of Random Variables
- Constraints Based Convex Belief Propagation
- Constructive Machine Learning
- Content-based Related Video Recommendations
- Contextual semibandits via supervised learning oracles
- Continual Learning and Deep Networks
- Convergence guarantees for kernel-based quadrature rules in misspecified settings
- Convex Two-Layer Modeling with Latent Structure
- Convolutional Neural Fabrics
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- Cooperative Graphical Models
- Cooperative Inverse Reinforcement Learning
- Coordinate-wise Power Method
- Coresets for Scalable Bayesian Logistic Regression
- Correlated-PCA: Principal Components' Analysis when Data and Noise are Correlated
- Coupled Generative Adversarial Networks
- CRF-CNN: Modeling Structured Information in Human Pose Estimation
- Crowdsourced Clustering: Querying Edges vs Triangles
- Crowdsourcing and Machine Learning
- Crowdsourcing: Beyond Label Generation
- Cyclades: Conflict-free Asynchronous Machine Learning
- Data driven estimation of Laplace-Beltrami operator
- Data Poisoning Attacks on Factorization-Based Collaborative Filtering
- Data Programming: Creating Large Training Sets, Quickly
- Deconvolving Feedback Loops in Recommender Systems
- DECOrrelated feature space partitioning for distributed sparse regression
- Deep ADMM-Net for Compressive Sensing MRI
- Deep Alternative Neural Network: Exploring Contexts as Early as Possible for Action Recognition
- Deep Exploration via Bootstrapped DQN
- deepGTTM-I: local grouping boundary analyzer
- Deep Learning for Action and Interaction
- Deep Learning for Predicting Human Strategic Behavior
- Deep Learning Games
- Deep Learning Models of the Retinal Response to Natural Scenes
- Deep Learning without Poor Local Minima
- DeepMath - Deep Sequence Models for Premise Selection
- Deep Neural Networks with Inexact Matching for Person Re-Identification
- Deep Reinforcement Learning
- Deep Reinforcement Learning for Robotics in DIANNE
- Deep Reinforcement Learning Through Policy Optimization
- Deep Submodular Functions: Definitions and Learning
- Dense Associative Memory for Pattern Recognition
- Density Estimation via Discrepancy Based Adaptive Sequential Partition
- Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions
- Designing smoothing functions for improved worst-case competitive ratio in online optimization
- Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling
- Dialog-based Language Learning
- Differential Privacy without Sensitivity
- Diffusion-Convolutional Neural Networks
- Dimensionality Reduction of Massive Sparse Datasets Using Coresets
- Dimension-Free Iteration Complexity of Finite Sum Optimization Problems
- Direct Feedback Alignment Provides Learning in Deep Neural Networks
- DISCO Nets : DISsimilarity COefficients Networks
- Discriminative Gaifman Models
- Disease Trajectory Maps
- Disentangling factors of variation in deep representation using adversarial training
- Distributed Flexible Nonlinear Tensor Factorization
- Domain Separation Networks
- Double Thompson Sampling for Dueling Bandits
- Doubly Convolutional Neural Networks
- Dual Decomposed Learning with Factorwise Oracle for Structural SVM of Large Output Domain
- Dual Learning for Machine Translation
- Dual Space Gradient Descent for Online Learning
- Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions
- Dynamic Filter Networks
- Dynamic Legged Robots
- Dynamic matrix recovery from incomplete observations under an exact low-rank constraint
- Dynamic Mode Decomposition with Reproducing Kernels for Koopman Spectral Analysis
- Dynamic Network Surgery for Efficient DNNs
- Edge-exchangeable graphs and sparsity
- Efficient and Robust Spiking Neural Circuit for Navigation Inspired by Echolocating Bats
- Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis
- Efficient High-Order Interaction-Aware Feature Selection Based on Conditional Mutual Information
- Efficient Methods for Deep Neural Networks
- Efficient Neural Codes under Metabolic Constraints
- Efficient Nonparametric Smoothness Estimation
- Efficient Second Order Online Learning by Sketching
- Efficient state-space modularization for planning: theory, behavioral and neural signatures
- Eliciting Categorical Data for Optimal Aggregation
- End-to-End Goal-Driven Web Navigation
- End-to-End Kernel Learning with Supervised Convolutional Kernel Networks
- End-to-end Learning for Speech and Audio Processing
- End-to-End Web Navigation
- Engineering Principles From Stable and Developing Brains
- Equality of Opportunity in Supervised Learning
- Error Analysis of Generalized Nyström Kernel Regression
- Estimating Nonlinear Neural Response Functions using GP Priors and Kronecker Methods
- Estimating the class prior and posterior from noisy positives and unlabeled data
- Estimating the Size of a Large Network and its Communities from a Random Sample
- Even Faster SVD Decomposition Yet Without Agonizing Pain
- Exact Recovery of Hard Thresholding Pursuit
- Examples are not enough, learn to criticize! Criticism for Interpretability
- Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters
- Exploiting Tradeoffs for Exact Recovery in Heterogeneous Stochastic Block Models
- Exponential expressivity in deep neural networks through transient chaos
- Exponential Family Embeddings
- Extreme Classification: Multi-class and Multi-label Learning in Extremely Large Label Spaces
- Fairness in Learning: Classic and Contextual Bandits
- Fast Active Set Methods for Online Spike Inference from Calcium Imaging
- Fast Algorithms for Robust PCA via Gradient Descent
- Fast and accurate spike sorting of high-channel count probes with KiloSort
- Fast and Flexible Monotonic Functions with Ensembles of Lattices
- Fast and Provably Good Seedings for k-Means
- Fast Distributed Submodular Cover: Public-Private Data Summarization
- Faster Projection-free Convex Optimization over the Spectrahedron
- Fast learning rates with heavy-tailed losses
- Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling
- Fast recovery from a union of subspaces
- Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimation
- Feature-distributed sparse regression: a screen-and-clean approach
- Feature selection in functional data classification with recursive maxima hunting
- f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
- Finding significant combinations of features in the presence of categorical covariates
- Finite-Dimensional BFRY Priors and Variational Bayesian Inference for Power Law Models
- Finite-Sample Analysis of Fixed-k Nearest Neighbor Density Functional Estimators
- Finite Sample Prediction and Recovery Bounds for Ordinal Embedding
- Flexible Models for Microclustering with Application to Entity Resolution
- Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities
- FPNN: Field Probing Neural Networks for 3D Data
- Full-Capacity Unitary Recurrent Neural Networks
- Fundamental Limits of Budget-Fidelity Trade-off in Label Crowdsourcing
- GAP Safe Screening Rules for Sparse-Group Lasso
- Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations
- Gaussian Processes for Survival Analysis
- Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back
- Generalized Correspondence-LDA Models (GC-LDA) for Identifying Functional Regions in the Brain
- General Tensor Spectral Co-clustering for Higher-Order Data
- Generating Images with Perceptual Similarity Metrics based on Deep Networks
- Generating Long-term Trajectories Using Deep Hierarchical Networks
- Generating Videos with Scene Dynamics
- Generative Adversarial Imitation Learning
- Generative Adversarial Networks
- Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data
- Geometric Dirichlet Means Algorithm for topic inference
- Global Analysis of Expectation Maximization for Mixtures of Two Gaussians
- Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods
- Global Optimality of Local Search for Low Rank Matrix Recovery
- Gradient-based Sampling: An Adaptive Importance Sampling for Least-squares
- Graph Clustering: Block-models and model free results
- Graphical Time Warping for Joint Alignment of Multiple Curves
- Graphons, mergeons, and so on!
- Greedy Feature Construction
- Guided Policy Search via Approximate Mirror Descent
- Hardness of Online Sleeping Combinatorial Optimization Problems
- Hierarchical Clustering via Spreading Metrics
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- High Dimensional Structured Superposition Models
- Higher-Order Factorization Machines
- High-Rank Matrix Completion and Clustering under Self-Expressive Models
- High resolution neural connectivity from incomplete tracing data using nonnegative spline regression
- Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than $O(1/\epsilon)$
- How Deep is the Feature Analysis underlying Rapid Visual Categorization?
- Human Decision-Making under Limited Time
- Hypothesis Testing in Unsupervised Domain Adaptation with Applications in Alzheimer's Disease
- Identification and Overidentification of Linear Structural Equation Models
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
- Imperfect Decision Makers: Admitting Real-World Rationality
- Improved Deep Metric Learning with Multi-class N-pair Loss Objective
- Improved Dropout for Shallow and Deep Learning
- Improved Error Bounds for Tree Representations of Metric Spaces
- Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
- Improved Techniques for Training GANs
- Improving PAC Exploration Using the Median Of Means
- Improving Variational Autoencoders with Inverse Autoregressive Flow
- Incremental Boosting Convolutional Neural Network for Facial Action Unit Recognition
- Incremental Variational Sparse Gaussian Process Regression
- Inference by Reparameterization in Neural Population Codes
- Infinite Hidden Semi-Markov Modulated Interaction Point Process
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Integrated perception with recurrent multi-task neural networks
- Intelligent Biosphere
- Interaction Networks for Learning about Objects, Relations and Physics
- Interaction Screening: Efficient and Sample-Optimal Learning of Ising Models
- Interactive musical improvisation with Magenta
- Interpretable Distribution Features with Maximum Testing Power
- Interpretable Machine Learning for Complex Systems
- Interpretable Nonlinear Dynamic Modeling of Neural Trajectories
- Intuitive Physics
- Iterative Refinement of the Approximate Posterior for Directed Belief Networks
- Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition
- Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization
- Joint quantile regression in vector-valued RKHSs
- Kernel Bayesian Inference with Posterior Regularization
- Kernel Observers: Systems-Theoretic Modeling and Inference of Spatiotemporally Evolving Processes
- k*-Nearest Neighbors: From Global to Local
- Kronecker Determinantal Point Processes
- Ladder Variational Autoencoders
- Large Margin Discriminant Dimensionality Reduction in Prediction Space
- Large Scale Computer Vision Systems
- Large-Scale Optimization: Beyond Stochastic Gradient Descent and Convexity
- Large-Scale Price Optimization via Network Flow
- Latent Attention For If-Then Program Synthesis
- Launch and Iterate: Reducing Prediction Churn
- Learnable Visual Markers
- Learned Region Sparsity and Diversity Also Predicts Visual Attention
- Learning About the Brain: Neuroimaging and Beyond
- Learning Additive Exponential Family Graphical Models via $\ell_{2,1}$-norm Regularized M-Estimation
- Learning a Metric Embedding for Face Recognition using the Multibatch Method
- Learning and Forecasting Opinion Dynamics in Social Networks
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Learning Bayesian networks with ancestral constraints
- Learning Bound for Parameter Transfer Learning
- Learning brain regions via large-scale online structured sparse dictionary learning
- Learning Deep Embeddings with Histogram Loss
- Learning Deep Parsimonious Representations
- Learning feed-forward one-shot learners
- Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs
- Learning HMMs with Nonparametric Emissions via Spectral Decompositions of Continuous Matrices
- Learning, Inference and Control of Multi-Agent Systems
- Learning Infinite RBMs with Frank-Wolfe
- Learning Influence Functions from Incomplete Observations
- Learning in Games: Robustness of Fast Convergence
- Learning in High Dimensions with Structure
- Learning Kernels with Random Features
- Learning Multiagent Communication with Backpropagation
- Learning Parametric Sparse Models for Image Super-Resolution
- Learning Sensor Multiplexing Design through Back-propagation
- Learning shape correspondence with anisotropic convolutional neural networks
- Learning Sparse Gaussian Graphical Models with Overlapping Blocks
- Learning Structured Sparsity in Deep Neural Networks
- Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methods
- Learning the Number of Neurons in Deep Networks
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Learning to learn by gradient descent by gradient descent
- Learning to Poke by Poking: Experiential Learning of Intuitive Physics
- Learning Transferrable Representations for Unsupervised Domain Adaptation
- Learning Tree Structured Potential Games
- Learning Treewidth-Bounded Bayesian Networks with Thousands of Variables
- Learning under uncertainty: a comparison between R-W and Bayesian approach
- Learning User Perceived Clusters with Feature-Level Supervision
- Learning values across many orders of magnitude
- Learning What and Where to Draw
- Learning with Tensors: Why Now and How?
- Let's Discuss: Learning Methods for Dialogue
- Leveraging Sparsity for Efficient Submodular Data Summarization
- Lifelong Learning with Weighted Majority Votes
- LightRNN: Memory and Computation-Efficient Recurrent Neural Networks
- Linear Contextual Bandits with Knapsacks
- Linear dynamical neural population models through nonlinear embeddings
- Linear Feature Encoding for Reinforcement Learning
- Linear-Memory and Decomposition-Invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes
- Linear Relaxations for Finding Diverse Elements in Metric Spaces
- Live Demo: Detecting Unexpected Obstacles for Self-Driving Cars
- Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences
- Local Minimax Complexity of Stochastic Convex Optimization
- Local Similarity-Aware Deep Feature Embedding
- Logically Complex Symbol Grounding for Interactive Robots by Seq2seq Learning with an LSTM-RNN
- Long-term Causal Effects via Behavioral Game Theory
- Low-Rank Regression with Tensor Responses
- Machine Intelligence @ NIPS
- Machine Learning and Likelihood-Free Inference in Particle Physics
- Machine Learning for Education
- Machine Learning for Health
- Machine Learning for Intelligent Transportation Systems
- Machine Learning for Spatiotemporal Forecasting
- Machine Learning in Computational Biology
- Machine Learning Systems
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Mapping Estimation for Discrete Optimal Transport
- Matching Networks for One Shot Learning
- Matrix Completion has No Spurious Local Minimum
- Maximal Sparsity with Deep Networks?
- Maximization of Approximately Submodular Functions
- Maximizing Influence in an Ising Network: A Mean-Field Optimal Solution
- Measuring Neural Net Robustness with Constraints
- Measuring the reliability of MCMC inference with bidirectional Monte Carlo
- Memory-Efficient Backpropagation Through Time
- MetaGrad: Multiple Learning Rates in Online Learning
- Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels
- Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning
- Minimizing Quadratic Functions in Constant Time
- Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum Games
- Mistake Bounds for Binary Matrix Completion
- Mixed Linear Regression with Multiple Components
- Mixed vine copulas as joint models of spike counts and local field potentials
- ML Foundations and Methods for Precision Medicine and Healthcare
- MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
- Monday Posters
- More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning
- Movidius Fathom: Deep Learning in a USB stick
- Multi-armed Bandits: Competing with Optimal Sequences
- Multimodal Residual Learning for Visual QA
- Multiple-Play Bandits in the Position-Based Model
- Multistage Campaigning in Social Networks
- Multi-step learning and underlying structure in statistical models
- Multivariate tests of association based on univariate tests
- Multi-view Anomaly Detection via Robust Probabilistic Latent Variable Models
- Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula
- Natural Language Processing for Computational Social Science
- Natural-Parameter Networks: A Class of Probabilistic Neural Networks
- Nearly Isometric Embedding by Relaxation
- Near-Optimal Smoothing of Structured Conditional Probability Matrices
- Nested Mini-Batch K-Means
- NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization
- Neural Abstract Machines & Program Induction
- Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks
- Neural Puppet
- Neural Universal Discrete Denoiser
- Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics
- Neurorobotics: A Chance for New Ideas, Algorithms and Approaches
- Neurorobotics: A Chance for New Ideas, Algorithms and Approaches (2nd day)
- New Liftable Classes for First-Order Probabilistic Inference
- Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling
- Nonconvex Optimization for Machine Learning: Theory and Practice
- Normalized Spectral Map Synchronization
- Nullhop: Flexibly efficient FPGA CNN accelerator driven by DAVIS neuromorphic vision sensor
- Nuts and Bolts of Building Applications using Deep Learning
- Object based Scene Representations using Fisher Scores of Local Subspace Projections
- Observational-Interventional Priors for Dose-Response Learning
- One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities
- On Explore-Then-Commit strategies
- On Graph Reconstruction via Empirical Risk Minimization: Fast Learning Rates and Scalability
- Online and Differentially-Private Tensor Decomposition
- Online Bayesian Moment Matching for Topic Modeling with Unknown Number of Topics
- Online Convex Optimization with Unconstrained Domains and Losses
- Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes
- Online Pricing with Strategic and Patient Buyers
- On Mixtures of Markov Chains
- On Multiplicative Integration with Recurrent Neural Networks
- On Regularizing Rademacher Observation Losses
- On Robustness of Kernel Clustering
- On the Recursive Teaching Dimension of VC Classes
- On Valid Optimal Assignment Kernels and Applications to Graph Classification
- Operator Variational Inference
- OPT 2016: Optimization for Machine Learning
- Optimal Architectures in a Solvable Model of Deep Networks
- Optimal Binary Classifier Aggregation for General Losses
- Optimal Black-Box Reductions Between Optimization Objectives
- Optimal Cluster Recovery in the Labeled Stochastic Block Model
- Optimal Learning for Multi-pass Stochastic Gradient Methods
- Optimal Sparse Linear Encoders and Sparse PCA
- Optimal spectral transportation with application to music transcription
- Optimal Tagging with Markov Chain Optimization
- Optimistic Bandit Convex Optimization
- Optimistic Gittins Indices
- Optimizing affinity-based binary hashing using auxiliary coordinates
- Optimizing the Optimizers
- Orthogonal Random Features
- PAC-Bayesian Theory Meets Bayesian Inference
- PAC Reinforcement Learning with Rich Observations
- Pairwise Choice Markov Chains
- Parameter Learning for Log-supermodular Distributions
- Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations
- People and machines: Public views on machine learning, and what this means for machine learning researchers
- PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
- Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
- Phased Exploration with Greedy Exploitation in Stochastic Combinatorial Partial Monitoring Games
- Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
- Poisson-Gamma dynamical systems
- Practical Bayesian Nonparametrics
- Predictive Learning
- Preference Completion from Partial Rankings
- Privacy Odometers and Filters: Pay-as-you-Go Composition
- Private Multi-Party Machine Learning
- Probabilistic Inference with Generating Functions for Poisson Latent Variable Models
- Probabilistic Linear Multistep Methods
- Probing the Compositionality of Intuitive Functions
- Professor Forcing: A New Algorithm for Training Recurrent Networks
- Project Malmo - Minecraft for AI Research
- Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images
- Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent
- Proximal Deep Structured Models
- Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization
- Pruning Random Forests for Prediction on a Budget
- Quantized Random Projections and Non-Linear Estimation of Cosine Similarity
- Quantum Perceptron Models
- Realistic Virtual Worlds and Human Actions for Video Understanding
- Real-time interactive sequence generation with Recurrent Neural Network ensembles
- Reconstructing Parameters of Spreading Models from Partial Observations
- Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates
- Refined Lower Bounds for Adversarial Bandits
- Regret Bounds for Non-decomposable Metrics with Missing Labels
- Regret of Queueing Bandits
- Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
- Regularized Nonlinear Acceleration
- Relevant sparse codes with variational information bottleneck
- Reliable Machine Learning in the Wild
- Rényi Divergence Variational Inference
- Representation Learning in Artificial and Biological Neural Networks
- Reproducible Research: the Case of the Human Microbiome
- Reshaped Wirtinger Flow for Solving Quadratic System of Equations
- Residual Networks Behave Like Ensembles of Relatively Shallow Networks
- RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism
- Review Networks for Caption Generation
- Reward Augmented Maximum Likelihood for Neural Structured Prediction
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
- Robust k-means: a Theoretical Revisit
- Robustness of classifiers: from adversarial to random noise
- Robust Spectral Detection of Global Structures in the Data by Learning a Regularization
- Safe and Efficient Off-Policy Reinforcement Learning
- Safe Exploration in Finite Markov Decision Processes with Gaussian Processes
- Safe Policy Improvement by Minimizing Robust Baseline Regret
- Sample Complexity of Automated Mechanism Design
- Sampling for Bayesian Program Learning
- Satisfying Real-world Goals with Dataset Constraints
- Scalable Adaptive Stochastic Optimization Using Random Projections
- Scaled Least Squares Estimator for GLMs in Large-Scale Problems
- Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages
- Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes
- Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much
- SDP Relaxation with Randomized Rounding for Energy Disaggregation
- Search Improves Label for Active Learning
- SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques
- Select-and-Sample for Spike-and-Slab Sparse Coding
- Selective inference for group-sparse linear models
- Semiparametric Differential Graph Models
- Sequential Neural Models with Stochastic Layers
- Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products
- Showing versus doing: Teaching by demonstration
- Simple and Efficient Weighted Minwise Hashing
- Single-Image Depth Perception in the Wild
- Single Pass PCA of Matrix Products
- Solving Marginal MAP Problems with NP Oracles and Parity Constraints
- Solving Random Systems of Quadratic Equations via Truncated Generalized Gradient Flow
- Sorting out typicality with the inverse moment matrix SOS polynomial
- SoundNet: Learning Sound Representations from Unlabeled Video
- SPALS: Fast Alternating Least Squares via Implicit Leverage Scores Sampling
- Sparse Support Recovery with Non-smooth Loss Functions
- Spatio-Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments
- Spatiotemporal Residual Networks for Video Action Recognition
- Spectral Learning of Dynamic Systems from Nonequilibrium Data
- Split LBI: An Iterative Regularization Path with Structural Sparsity
- Statistical Inference for Cluster Trees
- Statistical Inference for Pairwise Graphical Models Using Score Matching
- Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
- Stochastic Gradient Geodesic MCMC Methods
- Stochastic Gradient MCMC with Stale Gradients
- Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences
- Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo
- Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles
- Stochastic Online AUC Maximization
- Stochastic Optimization for Large-scale Optimal Transport
- Stochastic Structured Prediction under Bandit Feedback
- Stochastic Three-Composite Convex Minimization
- Stochastic Variance Reduction Methods for Saddle-Point Problems
- Stochastic Variational Deep Kernel Learning
- Strategic Attentive Writer for Learning Macro-Actions
- Structure-Blind Signal Recovery
- Structured Matrix Recovery via the Generalized Dantzig Selector
- Structured Prediction Theory Based on Factor Graph Complexity
- Structured Sparse Regression via Greedy Hard Thresholding
- Sublinear Time Orthogonal Tensor Decomposition
- Sub-sampled Newton Methods with Non-uniform Sampling
- Supervised learning through the lens of compression
- Supervised Learning with Tensor Networks
- Supervised Word Mover's Distance
- SURGE: Surface Regularized Geometry Estimation from a Single Image
- Swapout: Learning an ensemble of deep architectures
- Synthesis of MCMC and Belief Propagation
- Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
- Tagger: Deep Unsupervised Perceptual Grouping
- Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction
- Tensor Switching Networks
- Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity
- The Forget-me-not Process
- The Future of Gradient-Based Machine Learning Software
- The Future of Interactive Machine Learning
- The Generalized Reparameterization Gradient
- The Limits of Learning with Missing Data
- The Multi-fidelity Multi-armed Bandit
- The Multiple Quantile Graphical Model
- The Multiscale Laplacian Graph Kernel
- The non-convex Burer-Monteiro approach works on smooth semidefinite programs
- Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning
- Theory and Algorithms for Forecasting Non-Stationary Time Series
- The Parallel Knowledge Gradient Method for Batch Bayesian Optimization
- The Power of Adaptivity in Identifying Statistical Alternatives
- The Power of Optimization from Samples
- The Product Cut
- The Robustness of Estimator Composition
- The Sound of APALM Clapping: Faster Nonsmooth Nonconvex Optimization with Stochastic Asynchronous PALM
- Threshold Bandits, With and Without Censored Feedback
- Threshold Learning for Optimal Decision Making
- Tight Complexity Bounds for Optimizing Composite Objectives
- Time Series Workshop
- Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers
- Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity
- Towards an Artificial Intelligence for Data Science
- Towards Conceptual Compression
- Towards Unifying Hamiltonian Monte Carlo and Slice Sampling
- Tracking the Best Expert in Non-stationary Stochastic Environments
- Tractable Operations for Arithmetic Circuits of Probabilistic Models
- Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images
- Tree-Structured Reinforcement Learning for Sequential Object Localization
- Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation
- Understanding Probabilistic Sparse Gaussian Process Approximations
- Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
- Unified Methods for Exploiting Piecewise Linear Structure in Convex Optimization
- Unifying Count-Based Exploration and Intrinsic Motivation
- Universal Correspondence Network
- Unsupervised Domain Adaptation with Residual Transfer Networks
- Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA
- Unsupervised Learning for Physical Interaction through Video Prediction
- Unsupervised Learning from Noisy Networks with Applications to Hi-C Data
- Unsupervised Learning of 3D Structure from Images
- Unsupervised Learning of Spoken Language with Visual Context
- Unsupervised Risk Estimation Using Only Conditional Independence Structure
- Using Fast Weights to Attend to the Recent Past
- Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model
- Value Iteration Networks
- Variance Reduction in Stochastic Gradient Langevin Dynamics
- Variational Autoencoder for Deep Learning of Images, Labels and Captions
- Variational Bayes on Monte Carlo Steroids
- Variational Inference: Foundations and Modern Methods
- Variational Inference in Mixed Probabilistic Submodular Models
- Variational Information Maximization for Feature Selection
- Verification Based Solution for Structured MAB Problems
- VIME: Variational Information Maximizing Exploration
- Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
- Visual Question Answering with Question Representation Update (QRU)
- Wasserstein Training of Restricted Boltzmann Machines
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- "What If?" Inference and Learning of Hypothetical and Counterfactual Interventions in Complex Systems
- What Makes Objects Similar: A Unified Multi-Metric Learning Approach
- (Withdrawn)Only H is left: Near-tight Episodic PAC RL
- Without-Replacement Sampling for Stochastic Gradient Methods
- Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale