Downloads 2017
Number of events: 768
- 2017 NIPS Workshop on Machine Learning for Intelligent Transportation Systems
- 3D Surface-to-Structure Translation with Deep Convolutional Networks
- 6th Workshop on Automated Knowledge Base Construction (AKBC)
- A Bayesian Data Augmentation Approach for Learning Deep Models
- Accelerated consensus via Min-Sum Splitting
- Accelerated First-order Methods for Geodesically Convex Optimization on Riemannian Manifolds
- Accelerated Stochastic Greedy Coordinate Descent by Soft Thresholding Projection onto Simplex
- Acceleration and Averaging in Stochastic Descent Dynamics
- Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM
- A cortical neural network simulator for kids
- Acting and Interacting in the Real World: Challenges in Robot Learning
- Action Centered Contextual Bandits
- Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
- Active Exploration for Learning Symbolic Representations
- Active Learning from Peers
- AdaGAN: Boosting Generative Models
- Adaptive Accelerated Gradient Converging Method under H\"{o}lderian Error Bound Condition
- Adaptive Active Hypothesis Testing under Limited Information
- Adaptive Batch Size for Safe Policy Gradients
- Adaptive Bayesian Sampling with Monte Carlo EM
- Adaptive Classification for Prediction Under a Budget
- Adaptive Clustering through Semidefinite Programming
- Adaptive stimulus selection for optimizing neural population responses
- Adaptive SVRG Methods under Error Bound Conditions with Unknown Growth Parameter
- A Decomposition of Forecast Error in Prediction Markets
- A Deep Reinforcement Learning Chatbot
- A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering
- A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
- ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization
- Advances in Approximate Bayesian Inference
- Advances in Modeling and Learning Interactions from Complex Data
- Adversarial Ranking for Language Generation
- Adversarial Surrogate Losses for Ordinal Regression
- Adversarial Symmetric Variational Autoencoder
- Affine-Invariant Online Optimization and the Low-rank Experts Problem
- Affinity Clustering: Hierarchical Clustering at Scale
- A framework for Multi-A(rmed)/B(andit) Testing with Online FDR Control
- A General Framework for Robust Interactive Learning
- Aggressive Sampling for Multi-class to Binary Reduction with Applications to Text Classification
- A graph-theoretic approach to multitasking
- A Greedy Approach for Budgeted Maximum Inner Product Search
- AIDE: An algorithm for measuring the accuracy of probabilistic inference algorithms
- A KL-LUCB algorithm for Large-Scale Crowdsourcing
- A Learning Error Analysis for Structured Prediction with Approximate Inference
- ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
- Aligned Artificial Intelligence
- A Linear-Time Kernel Goodness-of-Fit Test
- (Almost) 50 shades of Bayesian Learning: PAC-Bayesian trends and insights
- Alternating Estimation for Structured High-Dimensional Multi-Response Models
- Alternating minimization for dictionary learning with random initialization
- A Meta-Learning Perspective on Cold-Start Recommendations for Items
- A Minimax Optimal Algorithm for Crowdsourcing
- A multi-agent reinforcement learning model of common-pool resource appropriation
- Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
- An Empirical Bayes Approach to Optimizing Machine Learning Algorithms
- An Empirical Study on The Properties of Random Bases for Kernel Methods
- An Error Detection and Correction Framework for Connectomics
- A New Alternating Direction Method for Linear Programming
- A New Theory for Matrix Completion
- A-NICE-MC: Adversarial Training for MCMC
- An inner-loop free solution to inverse problems using deep neural networks
- A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent
- Approximate Supermodularity Bounds for Experimental Design
- Approximation Algorithms for ℓ0-Low Rank Approximation
- Approximation and Convergence Properties of Generative Adversarial Learning
- Approximation Bounds for Hierarchical Clustering: Average Linkage, Bisecting K-means, and Local Search
- A Primer on Optimal Transport
- A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks
- A Regularized Framework for Sparse and Structured Neural Attention
- A Sample Complexity Measure with Applications to Learning Optimal Auctions
- A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis
- A Screening Rule for l1-Regularized Ising Model Estimation
- A Sharp Error Analysis for the Fused Lasso, with Application to Approximate Changepoint Screening
- A simple model of recognition and recall memory
- A simple neural network module for relational reasoning
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Asynchronous Coordinate Descent under More Realistic Assumptions
- Asynchronous Parallel Coordinate Minimization for MAP Inference
- Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin
- Attentional Pooling for Action Recognition
- Attention is All you Need
- A Unified Approach to Interpreting Model Predictions
- A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
- A Universal Analysis of Large-Scale Regularized Least Squares Solutions
- Avoiding Discrimination through Causal Reasoning
- Babble Labble: Learning from Natural Language Explanations
- Balancing information exposure in social networks
- Bandits Dueling on Partially Ordered Sets
- Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
- Bayesian Compression for Deep Learning
- Bayesian Deep Learning
- Bayesian Dyadic Trees and Histograms for Regression
- Bayesian GAN
- Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes
- Bayesian optimization for science and engineering
- Bayesian Optimization with Gradients
- Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model
- Best Response Regression
- Beyond normality: Learning sparse probabilistic graphical models in the non-Gaussian setting
- Beyond Parity: Fairness Objectives for Collaborative Filtering
- Beyond Worst-case: A Probabilistic Analysis of Affine Policies in Dynamic Optimization
- BigNeuro 2017: Analyzing brain data from nano to macroscale
- Boltzmann Exploration Done Right
- Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization
- Bregman Divergence for Stochastic Variance Reduction: Saddle-Point and Adversarial Prediction
- Bridging the Gap Between Value and Policy Based Reinforcement Learning
- Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent
- Causal Effect Inference with Deep Latent-Variable Models
- Certified Defenses for Data Poisoning Attacks
- Clone MCMC: Parallel High-Dimensional Gaussian Gibbs Sampling
- Clustering Billions of Reads for DNA Data Storage
- Clustering Stable Instances of Euclidean k-means.
- Clustering with Noisy Queries
- Coded Distributed Computing for Inverse Problems
- Cognitively Informed Artificial Intelligence: Insights From Natural Intelligence
- Cold-Start Reinforcement Learning with Softmax Policy Gradient
- Collaborate & Communicate: An exploration and practical skills workshop that builds on the experience of AIML experts who are both successful collaborators and great communicators.
- Collaborative Deep Learning in Fixed Topology Networks
- Collaborative PAC Learning
- Collapsed variational Bayes for Markov jump processes
- Collecting Telemetry Data Privately
- Communication-Efficient Distributed Learning of Discrete Distributions
- Compatible Reward Inverse Reinforcement Learning
- Competition track
- Compression-aware Training of Deep Networks
- Concentration of Multilinear Functions of the Ising Model with Applications to Network Data
- Concrete Dropout
- Conic Scan-and-Cover algorithms for nonparametric topic modeling
- Conservative Contextual Linear Bandits
- Consistent Multitask Learning with Nonlinear Output Relations
- Consistent Robust Regression
- Context Selection for Embedding Models
- Continual Learning with Deep Generative Replay
- Contrastive Learning for Image Captioning
- Controllable Invariance through Adversarial Feature Learning
- Convergence Analysis of Two-layer Neural Networks with ReLU Activation
- Convergence of Gradient EM on Multi-component Mixture of Gaussians
- Convergence rates of a partition based Bayesian multivariate density estimation method
- Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks
- Conversational AI - today's practice and tomorrow's potential
- Conversational Speech Search on Massive Audio Datasets
- Convolutional Gaussian Processes
- Convolutional Phase Retrieval
- Cortical microcircuits as gated-recurrent neural networks
- Cost efficient gradient boosting
- Counterfactual Fairness
- Countering Feedback Delays in Multi-Agent Learning
- Cross-Spectral Factor Analysis
- CTRL-Labs: Non-invasive Neural Interface
- Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs
- Deanonymization in the Bitcoin P2P Network
- Decoding with Value Networks for Neural Machine Translation
- Decomposable Submodular Function Minimization: Discrete and Continuous
- Decomposition-Invariant Conditional Gradient for General Polytopes with Line Search
- Deconvolutional Paragraph Representation Learning
- Decoupling "when to update" from "how to update"
- Deep Dynamic Poisson Factorization Model
- Deep Hyperalignment
- Deep Hyperspherical Learning
- Deep Lattice Networks and Partial Monotonic Functions
- Deep Learning at Supercomputer Scale
- Deep Learning: Bridging Theory and Practice
- Deep Learning for Physical Sciences
- Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
- Deep Learning for Robotics
- Deep Learning: Practice and Trends
- Deep Learning with Topological Signatures
- Deep Mean-Shift Priors for Image Restoration
- Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks
- Deep Neural Net implementations with FPGAs
- Deep Probabilistic Modelling with Gaussian Processes
- Deep Recurrent Neural Network-Based Identification of Precursor microRNAs
- Deep Reinforcement Learning from Human Preferences
- Deep Robotic Learning using Visual Imagination and Meta-Learning
- Deep Sets
- Deep Subspace Clustering Networks
- Deep Supervised Discrete Hashing
- Deep Voice 2: Multi-Speaker Neural Text-to-Speech
- Deliberation Networks: Sequence Generation Beyond One-Pass Decoding
- Detrended Partial Cross Correlation for Brain Connectivity Analysis
- Differentiable Learning of Logical Rules for Knowledge Base Reasoning
- Differentiable Learning of Submodular Functions
- Differentially private Bayesian learning on distributed data
- Differentially Private Empirical Risk Minimization Revisited: Faster and More General
- Differentially Private Machine Learning: Theory, Algorithms and Applications
- Diffusion Approximations for Online Principal Component Estimation and Global Convergence
- Dilated Recurrent Neural Networks
- Discovering Potential Correlations via Hypercontractivity
- Discrete Structures in Machine Learning
- Discriminative State Space Models
- Distral: Robust multitask reinforcement learning
- Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space
- Diving into the shallows: a computational perspective on large-scale shallow learning
- Do Deep Neural Networks Suffer from Crowding?
- Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization
- Doubly Stochastic Variational Inference for Deep Gaussian Processes
- DPSCREEN: Dynamic Personalized Screening
- DropoutNet: Addressing Cold Start in Recommender Systems
- Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis
- Dual Discriminator Generative Adversarial Nets
- Dualing GANs
- Dual Path Networks
- Dykstra's Algorithm, ADMM, and Coordinate Descent: Connections, Insights, and Extensions
- Dynamic-Depth Context Tree Weighting
- Dynamic Importance Sampling for Anytime Bounds of the Partition Function
- Dynamic Revenue Sharing
- Dynamic Routing Between Capsules
- Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning
- Early stopping for kernel boosting algorithms: A general analysis with localized complexities
- EEG-GRAPH: A Factor-Graph-Based Model for Capturing Spatial, Temporal, and Observational Relationships in Electroencephalograms
- Effective Parallelisation for Machine Learning
- Efficient and Flexible Inference for Stochastic Systems
- Efficient Approximation Algorithms for Strings Kernel Based Sequence Classification
- Efficient Modeling of Latent Information in Supervised Learning using Gaussian Processes
- Efficient Online Linear Optimization with Approximation Algorithms
- Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding
- Efficient Second-Order Online Kernel Learning with Adaptive Embedding
- Efficient Sublinear-Regret Algorithms for Online Sparse Linear Regression with Limited Observation
- Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems
- Eigen-Distortions of Hierarchical Representations
- Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks
- Electronic Screen Protector with Efficient and Robust Mobile Vision
- Elementary Symmetric Polynomials for Optimal Experimental Design
- ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
- Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
- Emergent Communication Workshop
- End-to-End Differentiable Proving
- Engineering and Reverse-Engineering Intelligence Using Probabilistic Programs, Program Induction, and Deep Learning
- Ensemble Sampling
- Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach
- Estimating High-dimensional Non-Gaussian Multiple Index Models via Stein’s Lemma
- Estimating Mutual Information for Discrete-Continuous Mixtures
- Estimation of the covariance structure of heavy-tailed distributions
- EX2: Exploration with Exemplar Models for Deep Reinforcement Learning
- Excess Risk Bounds for the Bayes Risk using Variational Inference in Latent Gaussian Models
- Expectation Propagation for t-Exponential Family Using q-Algebra
- Expectation Propagation with Stochastic Kinetic Model in Complex Interaction Systems
- Experimental Design for Learning Causal Graphs with Latent Variables
- #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
- Exploring Generalization in Deep Learning
- Extracting low-dimensional dynamics from multiple large-scale neural population recordings by learning to predict correlations
- Extreme Classification: Multi-class & Multi-label Learning in Extremely Large Label Spaces
- ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
- Fader Networks:Manipulating Images by Sliding Attributes
- Fair Clustering Through Fairlets
- Fairness in Machine Learning
- FALKON: An Optimal Large Scale Kernel Method
- Fast amortized inference of neural activity from calcium imaging data with variational autoencoders
- Fast Black-box Variational Inference through Stochastic Trust-Region Optimization
- Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers
- Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe
- Fast, Sample-Efficient Algorithms for Structured Phase Retrieval
- Fast-Slow Recurrent Neural Networks
- Fast-speed Intelligent Video Analytics using Deep Learning Algorithms on Low-power FPGA
- Federated Multi-Task Learning
- Few-Shot Adversarial Domain Adaptation
- Few-Shot Learning Through an Information Retrieval Lens
- f-GANs in an Information Geometric Nutshell
- Filtering Variational Objectives
- Finite sample analysis of the GTD Policy Evaluation Algorithms in Markov Setting
- First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization
- Fisher GAN
- Fitting Low-Rank Tensors in Constant Time
- Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data
- Flexible statistical inference for mechanistic models of neural dynamics
- Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation
- From Bayesian Sparsity to Gated Recurrent Nets
- From Parity to Preference-based Notions of Fairness in Classification
- From 'What If?' To 'What Next?' : Causal Inference and Machine Learning for Intelligent Decision Making
- From which world is your graph
- Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Gated Recurrent Convolution Neural Network for OCR
- Gauging Variational Inference
- Gaussian process based nonlinear latent structure discovery in multivariate spike train data
- Gaussian Quadrature for Kernel Features
- Generalization Properties of Learning with Random Features
- Generalized Linear Model Regression under Distance-to-set Penalties
- Generalizing GANs: A Turing Perspective
- Generating steganographic images via adversarial training
- Generative Local Metric Learning for Kernel Regression
- Geometric Deep Learning on Graphs and Manifolds
- Geometric Descent Method for Convex Composite Minimization
- Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks
- GibbsNet: Iterative Adversarial Inference for Deep Graphical Models
- Good Semi-supervised Learning That Requires a Bad GAN
- GP CaKe: Effective brain connectivity with causal kernels
- Gradient Descent Can Take Exponential Time to Escape Saddle Points
- Gradient descent GAN optimization is locally stable
- Gradient Episodic Memory for Continual Learning
- Gradient Methods for Submodular Maximization
- Gradients of Generative Models for Improved Discriminative Analysis of Tandem Mass Spectra
- Graph Matching via Multiplicative Update Algorithm
- Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees
- Group Additive Structure Identification for Kernel Nonparametric Regression
- Group Sparse Additive Machine
- Hash Embeddings for Efficient Word Representations
- Hiding Images in Plain Sight: Deep Steganography
- Hierarchical Attentive Recurrent Tracking
- Hierarchical Clustering Beyond the Worst-Case
- Hierarchical Implicit Models and Likelihood-Free Variational Inference
- Hierarchical Methods of Moments
- Hierarchical Reinforcement Learning
- Higher-Order Total Variation Classes on Grids: Minimax Theory and Trend Filtering Methods
- High-Order Attention Models for Visual Question Answering
- Hindsight Experience Replay
- Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples
- How regularization affects the critical points in linear networks
- Humans attributes extraction and search with a deep learning based real-time video analysis system
- Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs
- Hybrid Reward Architecture for Reinforcement Learning
- Hypothesis Transfer Learning via Transformation Functions
- Identification of Gaussian Process State Space Models
- Identifying Outlier Arms in Multi-Armed Bandit
- Imagination-Augmented Agents for Deep Reinforcement Learning
- Implicit Regularization in Matrix Factorization
- Improved Dynamic Regret for Non-degenerate Functions
- Improved Graph Laplacian via Geometric Self-Consistency
- Improved Training of Wasserstein GANs
- Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications
- Improving the Expected Improvement Algorithm
- Incorporating Side Information by Adaptive Convolution
- Independence clustering (without a matrix)
- Inductive Representation Learning on Large Graphs
- Inference in Graphical Models via Semidefinite Programming Hierarchies
- Inferring Generative Model Structure with Static Analysis
- Influence Maximization with ε-Almost Submodular Threshold Functions
- InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
- Information-theoretic analysis of generalization capability of learning algorithms
- Information Theoretic Properties of Markov Random Fields, and their Algorithmic Applications
- Inhomogeneous Hypergraph Clustering with Applications
- Integration Methods and Optimization Algorithms
- Interactive-Length Multi-Task Video Captioning with Cooperative Feedback
- Interactive Submodular Bandit
- Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning
- Interpretable and Globally Optimal Prediction for Textual Grounding using Image Concepts
- Interpreting, Explaining and Visualizing Deep Learning - Now what ?
- Introspective Classification with Convolutional Nets
- Invariance and Stability of Deep Convolutional Representations
- Inverse Filtering for Hidden Markov Models
- Inverse Reward Design
- Is Input Sparsity Time Possible for Kernel Low-Rank Approximation?
- Is the Bellman residual a bad proxy?
- Joint distribution optimal transportation for domain adaptation
- Kernel Feature Selection via Conditional Covariance Minimization
- Kernel functions based on triplet comparisons
- K-Medoids For K-Means Seeding
- k-Support and Ordered Weighted Sparsity for Overlapping Groups: Hardness and Algorithms
- Label Distribution Learning Forests
- Label Efficient Learning of Transferable Representations acrosss Domains and Tasks
- Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks
- Language Modeling with Recurrent Highway Hypernetworks
- Large-Scale Quadratically Constrained Quadratic Program via Low-Discrepancy Sequences
- Learned D-AMP: Principled Neural Network based Compressive Image Recovery
- Learned in Translation: Contextualized Word Vectors
- Learning Active Learning from Data
- Learning Affinity via Spatial Propagation Networks
- Learning a Multi-View Stereo Machine
- Learning A Structured Optimal Bipartite Graph for Co-Clustering
- Learning Causal Structures Using Regression Invariance
- Learning Chordal Markov Networks via Branch and Bound
- Learning Combinatorial Optimization Algorithms over Graphs
- Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
- Learning Disentangled Features: from Perception to Control
- Learning Disentangled Representations with Semi-Supervised Deep Generative Models
- Learning Efficient Object Detection Models with Knowledge Distillation
- Learning from Complementary Labels
- Learning from uncertain curves: The 2-Wasserstein metric for Gaussian processes
- Learning Graph Representations with Embedding Propagation
- Learning Hierarchical Information Flow with Recurrent Neural Modules
- Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity
- Learning in the Presence of Strategic Behavior
- Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition
- Learning Linear Dynamical Systems via Spectral Filtering
- Learning Low-Dimensional Metrics
- Learning Mixture of Gaussians with Streaming Data
- Learning Multiple Tasks with Multilinear Relationship Networks
- Learning multiple visual domains with residual adapters
- Learning Neural Representations of Human Cognition across Many fMRI Studies
- Learning on Distributions, Functions, Graphs and Groups
- Learning Overcomplete HMMs
- Learning Populations of Parameters
- Learning ReLUs via Gradient Descent
- Learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data
- Learning Spherical Convolution for Fast Features from 360° Imagery
- Learning State Representations
- Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding
- Learning to Compose Domain-Specific Transformations for Data Augmentation
- Learning to Inpaint for Image Compression
- Learning to Model the Tail
- Learning to Pivot with Adversarial Networks
- Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon
- Learning to See Physics via Visual De-animation
- Learning Unknown Markov Decision Processes: A Thompson Sampling Approach
- Learning with Average Top-k Loss
- Learning with Bandit Feedback in Potential Games
- Learning with Feature Evolvable Streams
- Learning with Limited Labeled Data: Weak Supervision and Beyond
- Libratus: Beating Top Humans in No-Limit Poker
- LightGBM: A Highly Efficient Gradient Boosting Decision Tree
- Limitations on Variance-Reduction and Acceleration Schemes for Finite Sums Optimization
- Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls
- Linearly constrained Gaussian processes
- Linear regression without correspondence
- Linear Time Computation of Moments in Sum-Product Networks
- Local Aggregative Games
- Log-normality and Skewness of Estimated State/Action Values in Reinforcement Learning
- Lookahead Bayesian Optimization with Inequality Constraints
- Lower bounds on the robustness to adversarial perturbations
- Machine Deception
- Machine Learning and Computer Security
- Machine Learning Challenges as a Research Tool
- Machine Learning for Audio Signal Processing (ML4Audio)
- Machine Learning for Creativity and Design
- Machine Learning for Health (ML4H) - What Parts of Healthcare are Ripe for Disruption by Machine Learning Right Now?
- Machine Learning for Molecules and Materials
- Machine Learning for the Developing World
- Machine Learning in Computational Biology
- Machine Learning on the Phone and other Consumer Devices
- Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent
- Magenta and deeplearn.js: Real-time Control of DeepGenerative Music Models in the Browser
- MAgent: A Many-Agent Reinforcement Learning Research Platform for Artificial Collective Intelligence
- Mapping distinct timescales of functional interactions among brain networks
- MarrNet: 3D Shape Reconstruction via 2.5D Sketches
- Masked Autoregressive Flow for Density Estimation
- MaskRNN: Instance Level Video Object Segmentation
- Matching neural paths: transfer from recognition to correspondence search
- Matching on Balanced Nonlinear Representations for Treatment Effects Estimation
- Matrix Calculus -- The Power of Symbolic Differentiation
- Matrix Norm Estimation from a Few Entries
- Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification
- Maximum Margin Interval Trees
- Maxing and Ranking with Few Assumptions
- Max-Margin Invariant Features from Transformed Unlabelled Data
- Mean Field Residual Networks: On the Edge of Chaos
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Medical Imaging meets NIPS
- Minimal Exploration in Structured Stochastic Bandits
- Minimax Estimation of Bandable Precision Matrices
- Minimizing a Submodular Function from Samples
- Min-Max Propagation
- Mixture-Rank Matrix Approximation for Collaborative Filtering
- ML Systems Workshop @ NIPS 2017
- MMD GAN: Towards Deeper Understanding of Moment Matching Network
- Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit
- Model evidence from nonequilibrium simulations
- Model-Powered Conditional Independence Test
- Modulating early visual processing by language
- Monte-Carlo Tree Search by Best Arm Identification
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
- Multi-Armed Bandits with Metric Movement Costs
- Multi-Information Source Optimization
- Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets
- Multimodal Learning and Reasoning for Visual Question Answering
- Multi-Objective Non-parametric Sequential Prediction
- Multi-output Polynomial Networks and Factorization Machines
- Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos
- Multiresolution Kernel Approximation for Gaussian Process Regression
- Multiscale Quantization for Fast Similarity Search
- Multiscale Semi-Markov Dynamics for Intracortical Brain-Computer Interfaces
- Multi-Task Learning for Contextual Bandits
- Multitask Spectral Learning of Weighted Automata
- Multi-View Decision Processes: The Helper-AI Problem
- Multi-view Matrix Factorization for Linear Dynamical System Estimation
- Multi-way Interacting Regression via Factorization Machines
- Natural Value Approximators: Learning when to Trust Past Estimates
- Nearest-Neighbor Sample Compression: Efficiency, Consistency, Infinite Dimensions
- Nearest Neighbors for Modern Applications with Massive Data: An Age-old Solution with New Challenges
- Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
- Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem
- Near-Optimal Edge Evaluation in Explicit Generalized Binomial Graphs
- Near Optimal Sketching of Low-Rank Tensor Regression
- Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee
- Neural Discrete Representation Learning
- Neural Expectation Maximization
- NeuralFDR: Learning Discovery Thresholds from Hypothesis Features
- Neural Networks for Efficient Bayesian Decoding of Natural Images from Retinal Neurons
- Neural Program Meta-Induction
- Neural system identification for large populations separating “what” and “where”
- Neural Variational Inference and Learning in Undirected Graphical Models
- NIPS 2017 Time Series Workshop
- NIPS Highlights (MLTrain), Learn How to code a paper with state of the art frameworks
- Noise-Tolerant Interactive Learning Using Pairwise Comparisons
- Nonbacktracking Bounds on the Influence in Independent Cascade Models
- Non-convex Finite-Sum Optimization Via SCSG Methods
- Nonlinear Acceleration of Stochastic Algorithms
- Nonlinear random matrix theory for deep learning
- Non-monotone Continuous DR-submodular Maximization: Structure and Algorithms
- Nonparametric Online Regression while Learning the Metric
- Non-parametric Structured Output Networks
- Non-Stationary Spectral Kernels
- Off-policy evaluation for slate recommendation
- OnACID: Online Analysis of Calcium Imaging Data in Real Time
- On Bayesian Deep Learning and Deep Bayesian Learning
- On Blackbox Backpropagation and Jacobian Sensing
- On clustering network-valued data
- One-Shot Imitation Learning
- One-Sided Unsupervised Domain Mapping
- On Fairness and Calibration
- On Frank-Wolfe and Equilibrium Computation
- Online control of the false discovery rate with decaying memory
- Online Convex Optimization with Stochastic Constraints
- Online Dynamic Programming
- Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback
- Online Learning for Multivariate Hawkes Processes
- Online Learning of Optimal Bidding Strategy in Repeated Multi-Commodity Auctions
- Online Learning with a Hint
- Online Learning with Transductive Regret
- Online multiclass boosting
- Online Prediction with Selfish Experts
- Online Reinforcement Learning in Stochastic Games
- Online to Offline Conversions, Universality and Adaptive Minibatch Sizes
- On Optimal Generalizability in Parametric Learning
- On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning
- On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models
- On Structured Prediction Theory with Calibrated Convex Surrogate Losses
- On Tensor Train Rank Minimization : Statistical Efficiency and Scalable Algorithm
- On the Complexity of Learning Neural Networks
- On the Consistency of Quick Shift
- On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks
- On-the-fly Operation Batching in Dynamic Computation Graphs
- On the Model Shrinkage Effect of Gamma Process Edge Partition Models
- On the Optimization Landscape of Tensor Decompositions
- On the Power of Truncated SVD for General High-rank Matrix Estimation Problems
- OPT 2017: Optimization for Machine Learning
- Optimal Sample Complexity of M-wise Data for Top-K Ranking
- Optimal Shrinkage of Singular Values Under Random Data Contamination
- Optimal Transport and Machine Learning
- Optimistic posterior sampling for reinforcement learning: worst-case regret bounds
- Optimized Pre-Processing for Discrimination Prevention
- Overcoming Catastrophic Forgetting by Incremental Moment Matching
- Parallel Streaming Wasserstein Barycenters
- Parameter-Free Online Learning via Model Selection
- Parametric Simplex Method for Sparse Learning
- Partial Hard Thresholding: Towards A Principled Analysis of Support Recovery
- PASS-GLM: polynomial approximate sufficient statistics for scalable Bayesian GLM inference
- Permutation-based Causal Inference Algorithms with Interventions
- Perturbative Black Box Variational Inference
- Phase Transitions in the Pooled Data Problem
- PixelGAN Autoencoders
- Pixels to Graphs by Associative Embedding
- Plan, Attend, Generate: Planning for Sequence-to-Sequence Models
- Poincaré Embeddings for Learning Hierarchical Representations
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Policy Gradient With Value Function Approximation For Collective Multiagent Planning
- Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication
- Polynomial time algorithms for dual volume sampling
- Population Matching Discrepancy and Applications in Deep Learning
- Pose Guided Person Image Generation
- Position-based Multiple-play Bandit Problem with Unknown Position Bias
- Positive-Unlabeled Learning with Non-Negative Risk Estimator
- Powering the next 100 years
- Practical Bayesian Optimization for Model Fitting with Bayesian Adaptive Direct Search
- Practical Data-Dependent Metric Compression with Provable Guarantees
- Practical Hash Functions for Similarity Estimation and Dimensionality Reduction
- Practical Locally Private Heavy Hitters
- Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network
- Predicting Scene Parsing and Motion Dynamics in the Future
- Predicting User Activity Level In Point Processes With Mass Transport Equation
- Predictive-State Decoders: Encoding the Future into Recurrent Networks
- Predictive State Recurrent Neural Networks
- PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
- Premise Selection for Theorem Proving by Deep Graph Embedding
- Preventing Gradient Explosions in Gated Recurrent Units
- Principles of Riemannian Geometry in Neural Networks
- Probabilistic Models for Integration Error in the Assessment of Functional Cardiac Models
- Probabilistic Rule Realization and Selection
- Process-constrained batch Bayesian optimisation
- Protein Interface Prediction using Graph Convolutional Networks
- Prototypical Networks for Few-shot Learning
- PRUNE: Preserving Proximity and Global Ranking for Network Embedding
- Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes
- QMDP-Net: Deep Learning for Planning under Partial Observability
- QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
- Quantifying how much sensory information in a neural code is relevant for behavior
- Query Complexity of Clustering with Side Information
- Question Asking as Program Generation
- Random Permutation Online Isotonic Regression
- Random Projection Filter Bank for Time Series Data
- Ranking Data with Continuous Labels through Oriented Recursive Partitions
- Real-Time Bidding with Side Information
- Real Time Image Saliency for Black Box Classifiers
- REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
- Reconstruct & Crush Network
- Reconstructing perceived faces from brain activations with deep adversarial neural decoding
- Recurrent Ladder Networks
- Recursive Sampling for the Nystrom Method
- Recycling Privileged Learning and Distribution Matching for Fairness
- Reducing Reparameterization Gradient Variance
- Regret Analysis for Continuous Dueling Bandit
- Regret Minimization in MDPs with Options without Prior Knowledge
- Regularized Modal Regression with Applications in Cognitive Impairment Prediction
- Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
- Reinforcement Learning under Model Mismatch
- Reinforcement Learning with People
- Reliable Decision Support using Counterfactual Models
- Renyi Differential Privacy Mechanisms for Posterior Sampling
- Repeated Inverse Reinforcement Learning
- Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
- Revenue Optimization with Approximate Bid Predictions
- Revisit Fuzzy Neural Network: Demystifying Batch Normalization and ReLU with Generalized Hamming Network
- Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces
- Riemannian approach to batch normalization
- Rigorous Dynamics and Consistent Estimation in Arbitrarily Conditioned Linear Systems
- Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes
- Robust Conditional Probabilities
- Robust Estimation of Neural Signals in Calcium Imaging
- Robust Hypothesis Test for Nonlinear Effect with Gaussian Processes
- Robust Imitation of Diverse Behaviors
- Robust Optimization for Non-Convex Objectives
- Rotting Bandits
- Runtime Neural Pruning
- Safe Adaptive Importance Sampling
- Safe and Nested Subgame Solving for Imperfect-Information Games
- Safe Model-based Reinforcement Learning with Stability Guarantees
- SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud
- Saliency-based Sequential Image Attention with Multiset Prediction
- Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions
- Scalable Demand-Aware Recommendation
- Scalable Generalized Linear Bandits: Online Computation and Hashing
- Scalable Levy Process Priors for Spectral Kernel Learning
- Scalable Log Determinants for Gaussian Process Kernel Learning
- Scalable Model Selection for Belief Networks
- Scalable Planning with Tensorflow for Hybrid Nonlinear Domains
- Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
- Scalable Variational Inference for Dynamical Systems
- SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
- Selective Classification for Deep Neural Networks
- Self-Normalizing Neural Networks
- Self-Supervised Intrinsic Image Decomposition
- Self-supervised Learning of Motion Capture
- Semisupervised Clustering, AND-Queries and Locally Encodable Source Coding
- Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks
- Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
- Sensomind: Democratizing deep learning for the food industry
- SGD Learns the Conjugate Kernel Class of the Network
- Shallow Updates for Deep Reinforcement Learning
- Shape and Material from Sound
- Sharkzor: Interactive Deep Learning for Image Triage, Sort and Summary
- Sharpness, Restart and Acceleration
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- Simple strategies for recovering inner products from coarsely quantized random projections
- Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization
- Sobolev Training for Neural Networks
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Solid Harmonic Wavelet Scattering: Predicting Quantum Molecular Energy from Invariant Descriptors of 3D Electronic Densities
- Solving Most Systems of Random Quadratic Equations
- Sparse Approximate Conic Hulls
- Sparse convolutional coding for neuronal assembly detection
- Sparse Embedded k-Means Clustering
- Spectrally-normalized margin bounds for neural networks
- Spectral Mixture Kernels for Multi-Output Gaussian Processes
- Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization
- Spherical convolutions and their application in molecular modelling
- Stabilizing Training of Generative Adversarial Networks through Regularization
- State Aware Imitation Learning
- Statistical Cost Sharing
- Statistical Relational Artificial Intelligence: Logic, Probability and Computation
- Stein Variational Gradient Descent as Gradient Flow
- Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference
- Stochastic and Adversarial Online Learning without Hyperparameters
- Stochastic Approximation for Canonical Correlation Analysis
- Stochastic Mirror Descent in Variationally Coherent Optimization Problems
- Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure
- Stochastic Submodular Maximization: The Case of Coverage Functions
- Straggler Mitigation in Distributed Optimization Through Data Encoding
- Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach
- Streaming Sparse Gaussian Process Approximations
- Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
- Structured Bayesian Pruning via Log-Normal Multiplicative Noise
- Structured Embedding Models for Grouped Data
- Structured Generative Adversarial Networks
- Style Transfer from Non-Parallel Text by Cross-Alignment
- Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues
- Subset Selection and Summarization in Sequential Data
- Subset Selection under Noise
- Subspace Clustering via Tangent Cones
- Successor Features for Transfer in Reinforcement Learning
- SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability
- SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks
- Symbol Grounding and Program Induction using Multi-modal instructions, Visual Cues and Eye Tracking.
- Synergies in Geometric Data Analysis (2nd day)
- Synergies in Geometric Data Analysis (TWO DAYS)
- Targeting EEG/LFP Synchrony with Neural Nets
- Task-based End-to-end Model Learning in Stochastic Optimization
- Teaching Machines, Robots, and Humans
- Teaching Machines to Describe Images with Natural Language Feedback
- Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks
- Tensor Biclustering
- TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
- Testing and Learning on Distributions with Symmetric Noise Invariance
- The Expressive Power of Neural Networks: A View from the Width
- The Expxorcist: Nonparametric Graphical Models Via Conditional Exponential Densities
- The future of gradient-based machine learning software & techniques
- The Importance of Communities for Learning to Influence
- The Marginal Value of Adaptive Gradient Methods in Machine Learning
- The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process
- The Numerics of GANs
- The power of absolute discounting: all-dimensional distribution estimation
- The Reversible Residual Network: Backpropagation Without Storing Activations
- The Scaling Limit of High-Dimensional Online Independent Component Analysis
- The Trouble with Bias
- The Unreasonable Effectiveness of Structure
- The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings
- Thinking Fast and Slow with Deep Learning and Tree Search
- Thy Friend is My Friend: Iterative Collaborative Filtering for Sparse Matrix Estimation
- Time-dependent spatially varying graphical models, with application to brain fMRI data analysis
- TincyYolo: Smaller still, faster, and more efficient
- Tomography of the London Underground: a Scalable Model for Origin-Destination Data
- Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System
- Toward Multimodal Image-to-Image Translation
- Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks
- Towards Accurate Binary Convolutional Neural Network
- Towards Generalization and Simplicity in Continuous Control
- Tractability in Structured Probability Spaces
- Training Deep Networks without Learning Rates Through Coin Betting
- Training Quantized Nets: A Deeper Understanding
- Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems
- Train longer, generalize better: closing the generalization gap in large batch training of neural networks
- Translation Synchronization via Truncated Least Squares
- Transparent and interpretable Machine Learning in Safety Critical Environments
- Triangle Generative Adversarial Networks
- Trimmed Density Ratio Estimation
- Triple Generative Adversarial Nets
- Unbiased estimates for linear regression via volume sampling
- Unbounded cache model for online language modeling with open vocabulary
- Unified representation of tractography and diffusion-weighted MRI data using sparse multidimensional arrays
- Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
- Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction
- Universal consistency and minimax rates for online Mondrian Forests
- Universal Style Transfer via Feature Transforms
- Unsupervised Image-to-Image Translation Networks
- Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
- Unsupervised Learning of Disentangled Representations from Video
- Unsupervised learning of object frames by dense equivariant image labelling
- Unsupervised Sequence Classification using Sequential Output Statistics
- Unsupervised Transformation Learning via Convex Relaxations
- Uprooting and Rerooting Higher-Order Graphical Models
- Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation
- VAE Learning via Stein Variational Gradient Descent
- VAIN: Attentional Multi-agent Predictive Modeling
- Value Prediction Network
- Variable Importance Using Decision Trees
- Variance-based Regularization with Convex Objectives
- Variational Inference for Gaussian Process Models with Linear Complexity
- Variational Inference via χ Upper Bound Minimization
- Variational Laws of Visual Attention for Dynamic Scenes
- Variational Memory Addressing in Generative Models
- Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
- VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
- Visual Interaction Networks: Learning a Physics Simulator from Video
- Visually grounded interaction and language
- Visual Reference Resolution using Attention Memory for Visual Dialog
- Wasserstein Learning of Deep Generative Point Process Models
- Welfare Guarantees from Data
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent
- When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness
- Why AI Will Make it Possible to Reprogram the Human Genome
- Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning
- Working hard to know your neighbor's margins: Local descriptor learning loss
- Workshop on Meta-Learning
- Workshop on Prioritising Online Content
- Workshop on Worm's Neural Information Processing (WNIP)
- YASS: Yet Another Spike Sorter
- Zap Q-Learning
- Z-Forcing: Training Stochastic Recurrent Networks