NIPS 2018 Papers

Browse

mini compact topic detail

To Trust Or Not To Trust A Classifier

Regularization Learning Networks: Deep Learning for Tabular Datasets

Probabilistic Neural Programmed Networks for Scene Generation

Loss Functions for Multiset Prediction

The Price of Privacy for Low-rank Factorization

Overcoming Language Priors in Visual Question Answering with Adversarial Regularization

Modular Networks: Learning to Decompose Neural Computation

On Binary Classification in Extreme Regions

Bayesian Model Selection Approach to Boundary Detection with Non-Local Priors

Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations

A Practical Algorithm for Distributed Clustering and Outlier Detection

Are ResNets Provably Better than Linear Predictors?

Scaling provable adversarial defenses

Provable Gaussian Embedding with One Observation

Leveraged volume sampling for linear regression

Neural Nearest Neighbors Networks

Adversarial vulnerability for any classifier

The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization

Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks

Scalable Robust Matrix Factorization with Nonconvex Loss

PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits

Lifelong Inverse Reinforcement Learning

Precision and Recall for Time Series

Acceleration through Optimistic No-Regret Dynamics

Active Learning for Non-Parametric Regression Using Purely Random Trees

Synthesize Policies for Transfer and Adaptation across Tasks and Environments

Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition

Multi-Task Zipping via Layer-wise Neuron Sharing

Random Feature Stein Discrepancies

A Simple Cache Model for Image Recognition

A Bayesian Nonparametric View on Count-Min Sketch

Efficient Anomaly Detection via Matrix Sketching

Confounding-Robust Policy Improvement

Neural Ordinary Differential Equations

Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo

Fairness Through Computationally-Bounded Awareness

Sequential Context Encoding for Duplicate Removal

On Learning Markov Chains

Generative modeling for protein structures

Hunting for Discriminatory Proxies in Linear Regression Models

Stochastic Composite Mirror Descent: Optimal Bounds with High Probabilities

Maximum-Entropy Fine Grained Classification

TETRIS: TilE-matching the TRemendous Irregular Sparsity

Gradient Sparsification for Communication-Efficient Distributed Optimization

e-SNLI: Natural Language Inference with Natural Language Explanations

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning

Fast and Effective Robustness Certification

Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach

RetGK: Graph Kernels based on Return Probabilities of Random Walks

Statistical mechanics of low-rank tensor decomposition

Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization

Towards Robust Detection of Adversarial Examples

Semidefinite relaxations for certifying robustness to adversarial examples

Non-delusional Q-learning and value-iteration

Nonparametric Density Estimation under Adversarial Losses

Unsupervised Learning of Shape and Pose with Differentiable Point Clouds

Moonshine: Distilling with Cheap Convolutions

Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions

Stein Variational Gradient Descent as Moment Matching

Context-aware Synthesis and Placement of Object Instances

Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples

Improved Expressivity Through Dendritic Neural Networks

Efficient Loss-Based Decoding on Graphs for Extreme Classification

Predictive Uncertainty Estimation via Prior Networks

Efficient online algorithms for fast-rate regret bounds under sparsity

Extracting Relationships by Multi-Domain Matching

BRITS: Bidirectional Recurrent Imputation for Time Series

Incorporating Context into Language Encoding Models for fMRI

Training Neural Networks Using Features Replay

Sharp Bounds for Generalized Uniformity Testing

Assessing Generative Models via Precision and Recall

Explaining Deep Learning Models -- A Bayesian Non-parametric Approach

Mallows Models for Top-k Lists

Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions

Bayesian Semi-supervised Learning with Graph Gaussian Processes

Neighbourhood Consensus Networks

Mental Sampling in Multimodal Representations

Transfer of Deep Reactive Policies for MDP Planning

Sparse PCA from Sparse Linear Regression

Contrastive Learning from Pairwise Measurements

Computationally and statistically efficient learning of causal Bayes nets using path queries

Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks

Topkapi: Parallel and Fast Sketches for Finding Top-K Frequent Elements

The Price of Fair PCA: One Extra dimension

Point process latent variable models of larval zebrafish behavior

MixLasso: Generalized Mixed Regression via Convex Atomic-Norm Regularization

Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices

Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues

Learning Temporal Point Processes via Reinforcement Learning

Connecting Optimization and Regularization Paths

Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds

GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking

Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions

Removing Hidden Confounding by Experimental Grounding

Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Language

DropBlock: A regularization method for convolutional networks

Joint Autoregressive and Hierarchical Priors for Learned Image Compression

Robust Subspace Approximation in a Stream

Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems

Bias and Generalization in Deep Generative Models: An Empirical Study

Differentially Private Change-Point Detection

Streamlining Variational Inference for Constraint Satisfaction Problems

With Friends Like These, Who Needs Adversaries?

Benefits of over-parameterization with EM

Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons

Understanding Regularized Spectral Clustering via Graph Conductance

Learning Beam Search Policies via Imitation Learning

Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenters

Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning

Data-Driven Clustering via Parameterized Lloyd's Families

Sketching Method for Large Scale Combinatorial Inference

Bayesian Structure Learning by Recursive Bootstrap

The Sparse Manifold Transform

Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices

Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

Discretely Relaxing Continuous Variables for tractable Variational Inference

Temporal alignment and latent Gaussian process factor inference in population spike trains

Fast deep reinforcement learning using online adjustments from the past

Diversity-Driven Exploration Strategy for Deep Reinforcement Learning

Improved Network Robustness with Adversary Critic

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior

Bounded-Loss Private Prediction Markets

Complex Gated Recurrent Neural Networks

Regret Bounds for Online Portfolio Selection with a Cardinality Constraint

Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise

Gaussian Process Prior Variational Autoencoders

PCA of high dimensional random walks with comparison to neural network training

Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders

Deep Generative Models with Learnable Knowledge Constraints

Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution

Learning Abstract Options

Predictive Approximate Bayesian Computation via Saddle Points

Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound

Glow: Generative Flow with Invertible 1x1 Convolutions

Learning to Solve SMT Formulas

Convex Elicitation of Continuous Properties

Lifted Weighted Mini-Bucket

Learning and Inference in Hilbert Space with Quantum Graphical Models

Synaptic Strength For Convolutional Neural Network

Robustness of conditional GANs to noisy labels

Mesh-TensorFlow: Deep Learning for Supercomputers

Learning to Share and Hide Intentions using Information Regularization

Total stochastic gradient algorithms and applications in reinforcement learning

Learning with SGD and Random Features

Improving Simple Models with Confidence Profiles

Human-in-the-Loop Interpretability Prior

A Retrieve-and-Edit Framework for Predicting Structured Outputs

Robust Learning of Fixed-Structure Bayesian Networks

Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming

Bayesian Nonparametric Spectral Estimation

A Spectral View of Adversarially Robust Features

Blockwise Parallel Decoding for Deep Autoregressive Models

Low-Rank Tucker Decomposition of Large Tensors Using TensorSketch

On Markov Chain Gradient Descent

Scalable Laplacian K-modes

Maximizing acquisition functions for Bayesian optimization

Learning To Learn Around A Common Mean

Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network

Blind Deconvolutional Phase Retrieval via Convex Programming

Testing for Families of Distributions via the Fourier Transform

Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams

Using Large Ensembles of Control Variates for Variational Inference

Dynamic Network Model from Partial Observations

Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing

Neural Voice Cloning with a Few Samples

Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization

Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies

Learning Invariances using the Marginal Likelihood

Learning to Reason with Third Order Tensor Products

Object-Oriented Dynamics Predictor

Unsupervised Depth Estimation, 3D Face Rotation and Replacement

Learning to Specialize with Knowledge Distillation for Visual Question Answering

Entropy Rate Estimation for Markov Chains with Large State Space

Generalization Bounds for Uniformly Stable Algorithms

Uplift Modeling from Separate Labels

Latent Alignment and Variational Attention

Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation

Global Non-convex Optimization with Discretized Diffusions

ATOMO: Communication-efficient Learning via Atomic Sparsification

Deep Anomaly Detection Using Geometric Transformations

Online Robust Policy Learning in the Presence of Unknown Adversaries

Improving Explorability in Variational Inference with Annealed Variational Objectives

Variance-Reduced Stochastic Gradient Descent on Streaming Data

Adaptive Methods for Nonconvex Optimization

Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models

Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport

Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization

Improving Online Algorithms via ML Predictions

Implicit Bias of Gradient Descent on Linear Convolutional Networks

Towards Deep Conversational Recommendations

Ex ante coordination and collusion in zero-sum multi-player extensive-form games

The emergence of multiple retinal cell types through efficient coding of natural movies

Theoretical guarantees for EM under misspecified Gaussian mixture models

Trading robust representations for sample complexity through self-supervised visual experience

DAGs with NO TEARS: Continuous Optimization for Structure Learning

Probabilistic Model-Agnostic Meta-Learning

Reinforcement Learning for Solving the Vehicle Routing Problem

Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis

Coupled Variational Bayes via Optimization Embedding

Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation

Identification and Estimation of Causal Effects from Dependent Data

Learning Attractor Dynamics for Generative Memory

Deepcode: Feedback Codes via Deep Learning

PAC-Bayes bounds for stable algorithms with instance-dependent priors

Learning convex bounds for linear quadratic control policy synthesis

Multi-objective Maximization of Monotone Submodular Functions with Cardinality Constraint

An intriguing failing of convolutional neural networks and the CoordConv solution

PAC-Bayes Tree: weighted subtrees with guarantees

Neural Proximal Gradient Descent for Compressive Imaging

The Global Anchor Method for Quantifying Linguistic Shifts and Domain Adaptation

Statistical and Computational Trade-Offs in Kernel K-Means

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures

Invertibility of Convolutional Generative Networks from Partial Measurements

Representer Point Selection for Explaining Deep Neural Networks

Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization

Co-regularized Alignment for Unsupervised Domain Adaptation

Sanity Checks for Saliency Maps

SNIPER: Efficient Multi-Scale Training

Hardware Conditioned Policies for Multi-Robot Transfer Learning

Deep Dynamical Modeling and Control of Unsteady Fluid Flows

Coordinate Descent with Bandit Sampling

Watch Your Step: Learning Node Embeddings via Graph Attention

Beyond Grids: Learning Graph Representations for Visual Recognition

Reducing Network Agnostophobia

Learning and Testing Causal Models with Interventions

Quadrature-based features for kernel approximation

The Effect of Network Width on the Performance of Large-batch Training

Phase Retrieval Under a Generative Prior

Visual Reinforcement Learning with Imagined Goals

The Sample Complexity of Semi-Supervised Learning with Nonparametric Mixture Models

Learning SMaLL Predictors

Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias

The Importance of Sampling inMeta-Reinforcement Learning

Iterative Value-Aware Model Learning

Learning Safe Policies with Expert Guidance

A Stein variational Newton method

Balanced Policy Evaluation and Learning

Learning Compressed Transforms with Low Displacement Rank

Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds

Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data

Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features

Exploration in Structured Reinforcement Learning

Adaptive Path-Integral Autoencoders: Representation Learning and Planning for Dynamical Systems

Legendre Decomposition for Tensors

Flexible neural representation for physics prediction

Reversible Recurrent Neural Networks

Group Equivariant Capsule Networks

Invariant Representations without Adversarial Training

GLoMo: Unsupervised Learning of Transferable Relational Graphs

FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network

Wavelet regression and additive models for irregularly spaced data

Inferring Latent Velocities from Weather Radar Data using Gaussian Processes

Online Learning of Quantum States

Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels

Improving Neural Program Synthesis with Inferred Execution Traces

A Structured Prediction Approach for Label Ranking

Distributed Multitask Reinforcement Learning with Quadratic Convergence

Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes

A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite Matrices

Differential Privacy for Growing Databases

Estimators for Multivariate Information Measures in General Probability Spaces

Uniform Convergence of Gradients for Non-Convex Learning and Optimization

SING: Symbol-to-Instrument Neural Generator

Reinforcement Learning of Theorem Proving

Orthogonally Decoupled Variational Gaussian Processes

Randomized Prior Functions for Deep Reinforcement Learning

Data Amplification: A Unified and Competitive Approach to Property Estimation

Automatic differentiation in ML: Where we are and where we should be going

Compact Representation of Uncertainty in Clustering

Learning Plannable Representations with Causal InfoGAN

DeepPINK: reproducible feature selection in deep neural networks

Adversarial Regularizers in Inverse Problems

Clustering Redemption–Beyond the Impossibility of Kleinberg’s Axioms

Dendritic cortical microcircuits approximate the backpropagation algorithm

Learning without the Phase: Regularized PhaseMax Achieves Optimal Sample Complexity

A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks

Co-teaching: Robust training of deep neural networks with extremely noisy labels

A convex program for bilinear inversion of sparse vectors

Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization

Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

Transfer Learning with Neural AutoML

Learning Conditioned Graph Structures for Interpretable Visual Question Answering

HOUDINI: Lifelong Learning as Program Synthesis

Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects

Adversarial Multiple Source Domain Adaptation

Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition

Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds

On preserving non-discrimination when combining expert advice

Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images

Thwarting Adversarial Examples: An $L_0$-Robust Sparse Fourier Transform

Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages

Information-theoretic Limits for Community Detection in Network Models

Teaching Inverse Reinforcement Learners via Features and Demonstrations

Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks

Scaling Gaussian Process Regression with Derivatives

An Improved Analysis of Alternating Minimization for Structured Multi-Response Regression

Binary Classification from Positive-Confidence Data

Learning to Play With Intrinsically-Motivated, Self-Aware Agents

Neural Tangent Kernel: Convergence and Generalization in Neural Networks

Deep Poisson gamma dynamical systems

Non-metric Similarity Graphs for Maximum Inner Product Search

Meta-Learning MCMC Proposals

Contextual Stochastic Block Models

Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity

Generalisation of structural knowledge in the hippocampal-entorhinal system

The promises and pitfalls of Stochastic Gradient Langevin Dynamics

Distributionally Robust Graphical Models

Data-dependent PAC-Bayes priors via differential privacy

Online Reciprocal Recommendation with Theoretical Performance Guarantees

Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs

Constructing Unrestricted Adversarial Examples with Generative Models

Bilevel learning of the Group Lasso structure

Wasserstein Distributionally Robust Kalman Filtering

Differentiable MPC for End-to-end Planning and Control

Efficient Online Portfolio with Logarithmic Regret

Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion

Algorithms and Theory for Multiple-Source Adaptation

How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective

Hamiltonian Variational Auto-Encoder

Variational Bayesian Monte Carlo

Modelling and unsupervised learning of symmetric deformable object categories

Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data

Proximal Graphical Event Models

Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training

Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes

The challenge of realistic music generation: modelling raw audio at scale

Stochastic Expectation Maximization with Variance Reduction

Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data

Bayesian Control of Large MDPs with Unknown Dynamics in Data-Poor Environments

Spectral Signatures in Backdoor Attacks

Submodular Maximization via Gradient Ascent: The Case of Deep Submodular Functions

A General Method for Amortizing Variational Filtering

A Lyapunov-based Approach to Safe Reinforcement Learning

Learning to Repair Software Vulnerabilities with Generative Adversarial Networks

Graphical model inference: Sequential Monte Carlo meets deterministic approximations

Approximate Knowledge Compilation by Online Collapsed Importance Sampling

Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation

Robust Hypothesis Testing Using Wasserstein Uncertainty Sets

Does mitigating ML's impact disparity require treatment disparity?

Neural Arithmetic Logic Units

A Reduction for Efficient LDA Topic Reconstruction

Distributed $k$-Clustering for Data with Heavy Noise

Dirichlet belief networks for topic structure learning

Credit Assignment For Collective Multiagent RL With Global Rewards

RenderNet: A deep convolutional network for differentiable rendering from 3D shapes

Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization

Reward learning from human preferences and demonstrations in Atari

VideoCapsuleNet: A Simplified Network for Action Detection

On Neuronal Capacity

Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo

Towards Robust Interpretability with Self-Explaining Neural Networks

Monte-Carlo Tree Search for Constrained POMDPs

Deep State Space Models for Time Series Forecasting

Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding

Depth-Limited Solving for Imperfect-Information Games

Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks

Neural Architecture Optimization

Training Deep Neural Networks with 8-bit Floating Point Numbers

Understanding Batch Normalization

Preference Based Adaptation for Learning Objectives

Stochastic Cubic Regularization for Fast Nonconvex Optimization

Constrained Graph Variational Autoencoders for Molecule Design

Communication Compression for Decentralized Training

Improved Algorithms for Collaborative PAC Learning

Diffusion Maps for Textual Network Embedding

Scalar Posterior Sampling with Applications

Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo

Learning Loop Invariants for Program Verification

cpSGD: Communication-efficient and differentially-private distributed SGD

Breaking the Activation Function Bottleneck through Adaptive Parameterization

GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration

Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction

Rectangular Bounding Process

Knowledge Distillation by On-the-Fly Native Ensemble

Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

Constrained Cross-Entropy Method for Safe Reinforcement Learning

Simple, Distributed, and Accelerated Probabilistic Programming

Towards Text Generation with Adversarially Learned Neural Outlines

Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis

Adaptive Learning with Unknown Information Flows

Constant Regret, Generalized Mixability, and Mirror Descent

Out-of-Distribution Detection using Multiple Semantic Label Representations

Multi-Agent Generative Adversarial Imitation Learning

Revisiting $(\epsilon, \gamma, \tau)$-similarity learning for domain adaptation

How to tell when a clustering is (approximately) correct using convex relaxations

A Bayesian Approach to Generative Adversarial Imitation Learning

Generalisation in humans and deep neural networks

Stochastic Chebyshev Gradient Descent for Spectral Optimization

Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem

Non-Adversarial Mapping with VAEs

Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces

Bayesian Model-Agnostic Meta-Learning

Unsupervised Text Style Transfer using Language Models as Discriminators

Disconnected Manifold Learning for Generative Adversarial Networks

Learning Attentional Communication for Multi-Agent Cooperation

REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis

Training Deep Models Faster with Robust, Approximate Importance Sampling

A probabilistic population code based on neural samples

Deep Homogeneous Mixture Models: Representation, Separation, and Approximation

Implicit Probabilistic Integrators for ODEs

Chaining Mutual Information and Tightening Generalization Bounds

Provably Correct Automatic Sub-Differentiation for Qualified Programs

Relational recurrent neural networks

Causal Inference with Noisy and Missing Covariates via Matrix Factorization

Distributed Multi-Player Bandits - a Game of Thrones Approach

Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features

Stimulus domain transfer in recurrent models for large scale cortical population prediction on video

Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies

Dual Policy Iteration

Causal Inference via Kernel Deviance Measures

Scalable Hyperparameter Transfer Learning

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

Bayesian Alignments of Warped Multi-Output Gaussian Processes

End-to-End Differentiable Physics for Learning and Control

Model-Agnostic Private Learning

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

rho-POMDPs have Lipschitz-Continuous epsilon-Optimal Value Functions

Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss

Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks

BRUNO: A Deep Recurrent Model for Exchangeable Data

Efficient Convex Completion of Coupled Tensors using Coupled Nuclear Norms

Differentially Private Testing of Identity and Closeness of Discrete Distributions

Bandit Learning with Implicit Feedback

Unorganized Malicious Attacks Detection

Stochastic Nonparametric Event-Tensor Decomposition

Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses

Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks

Diminishing Returns Shape Constraints for Interpretability and Regularization

Policy Regret in Repeated Games

M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search

On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

Heterogeneous Multi-output Gaussian Process Prediction

Maximizing Induced Cardinality Under a Determinantal Point Process

Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation

Bayesian Adversarial Learning

Large-Scale Stochastic Sampling from the Probability Simplex

Generative Probabilistic Novelty Detection with Adversarial Autoencoders

Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders

GILBO: One Metric to Measure Them All

A Theory-Based Evaluation of Nearest Neighbor Models Put Into Practice

A Probabilistic U-Net for Segmentation of Ambiguous Images

On gradient regularizers for MMD GANs

CatBoost: unbiased boosting with categorical features

Contamination Attacks and Mitigation in Multi-Party Machine Learning

Banach Wasserstein GAN

Model-based targeted dimensionality reduction for neuronal population data

Query K-means Clustering and the Double Dixie Cup Problem

Unsupervised Learning of Artistic Styles with Archetypal Style Analysis

Approximating Real-Time Recurrent Learning with Random Kronecker Factors

On Coresets for Logistic Regression

Proximal SCOPE for Distributed Sparse Learning

Representation Learning of Compositional Data

Modeling Dynamic Missingness of Implicit Feedback for Recommendation

Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks

Compact Generalized Non-local Network

Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation

Size-Noise Tradeoffs in Generative Networks

The Everlasting Database: Statistical Validity at a Fair Price

L4: Practical loss-based stepsize adaptation for deep learning

Learning Latent Subspaces in Variational Autoencoders

Online Adaptive Methods, Universality and Acceleration

A no-regret generalization of hierarchical softmax to extreme multi-label classification

Bayesian Distributed Stochastic Gradient Descent

On the Local Hessian in Back-propagation

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation

Multi-domain Causal Structure Learning in Linear Systems

Turbo Learning for CaptionBot and DrawingBot

ResNet with one-neuron hidden layers is a Universal Approximator

Visualizing the Loss Landscape of Neural Nets

Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences

The Limits of Post-Selection Generalization

Learning to Teach with Dynamic Loss Functions

On Controllable Sparse Alternatives to Softmax

LF-Net: Learning Local Features from Images

Efficient Formal Safety Analysis of Neural Networks

Algebraic tests of general Gaussian latent tree models

Deep Neural Networks with Box Convolutions

Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization

Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling

Deep State Space Models for Unconditional Word Generation

SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient

The Cluster Description Problem - Complexity Results, Formulations and Approximations

Exponentially Weighted Imitation Learning for Batched Historical Data

Online convex optimization for cumulative constraints

Transfer of Value Functions via Variational Methods

Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming

Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models

Deep Structured Prediction with Nonlinear Output Transformations

Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning

MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models

Recurrent Transformer Networks for Semantic Correspondence

Learning towards Minimum Hyperspherical Energy

Graphical Generative Adversarial Networks

Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer

Automating Bayesian optimization with Bayesian optimization

Information Constraints on Auto-Encoding Variational Bayes

Approximation algorithms for stochastic clustering

Exact natural gradient in deep linear networks and its application to the nonlinear case

Memory Replay GANs: Learning to Generate New Categories without Forgetting

Constructing Fast Network through Deconstruction of Convolution

Learning to Infer Graphics Programs from Hand-Drawn Images

Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence

Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks

Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification

Variational Learning on Aggregate Outputs with Gaussian Processes

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

Deep Generative Models for Distribution-Preserving Lossy Compression

Masking: A New Perspective of Noisy Supervision

Neural Interaction Transparency (NIT): Disentangling Learned Interactions for Improved Interpretability

Dual Swap Disentangling

The Convergence of Sparsified Gradient Methods

On GANs and GMMs

Unsupervised Video Object Segmentation for Deep Reinforcement Learning

A Bayes-Sard Cubature Method

Computing Kantorovich-Wasserstein Distances on $d$-dimensional histograms using $(d+1)$-partite graphs

Adversarially Robust Optimization with Gaussian Processes

Diverse Ensemble Evolution: Curriculum Data-Model Marriage

Variational Inference with Tail-adaptive f-Divergence

CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces

Learning to Multitask

Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

Critical initialisation for deep signal propagation in noisy rectifier neural networks

Insights on representational similarity in neural networks with canonical correlation

Learning convex polytopes with margin

Online Improper Learning with an Approximation Oracle

Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance

Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity

On Fast Leverage Score Sampling and Optimal Learning

Manifold Structured Prediction

Contextual Pricing for Lipschitz Buyers

Bandit Learning in Concave N-Person Games

Efficient inference for time-varying behavior during learning

How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery?

Learning Others' Intentional Models in Multi-Agent Settings Using Interactive POMDPs

Occam's razor is insufficient to infer the preferences of irrational agents

A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization

Community Exploration: From Offline Optimization to Online Learning

Estimating Learnability in the Sublinear Data Regime

Middle-Out Decoding

Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames

Reparameterization Gradient for Non-differentiable Models

Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation

Learning Concave Conditional Likelihood Models for Improved Analysis of Tandem Mass Spectra

Differentially Private k-Means with Constant Multiplicative Error

Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing

Learning a latent manifold of odor representations from neural responses in piriform cortex

Multimodal Generative Models for Scalable Weakly-Supervised Learning

First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time

Hyperbolic Neural Networks

A Convex Duality Framework for GANs

Fully Understanding The Hashing Trick

Learning Task Specifications from Demonstrations

A Dual Framework for Low-rank Tensor Completion

Link Prediction Based on Graph Neural Networks

Experimental Design for Cost-Aware Learning of Causal Graphs

Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit task

Scalable methods for 8-bit training of neural networks

The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network

Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation

Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation

Learning in Games with Lossy Feedback

Generalizing to Unseen Domains via Adversarial Data Augmentation

Meta-Reinforcement Learning of Structured Exploration Strategies

Causal Inference and Mechanism Clustering of A Mixture of Additive Noise Models

Unsupervised Adversarial Invariance

Content preserving text generation with attribute controls

Horizon-Independent Minimax Linear Regression

Power-law efficient neural codes provide general link between perceptual bias and discriminability

ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions

Policy Optimization via Importance Sampling

Multi-armed Bandits with Compensation

Contour location via entropy reduction leveraging multiple information sources

Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model

Practical exact algorithm for trembling-hand equilibrium refinements in games

Neural Edit Operations for Biological Sequences

LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning

Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance

Supervising Unsupervised Learning

Nonparametric Bayesian Lomax delegate racing for survival analysis with competing risks

GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training

Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning

Exploiting Numerical Sparsity for Efficient Learning : Faster Eigenvector Computation and Regression

Task-Driven Convolutional Recurrent Models of the Visual System

Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization

Efficient Neural Network Robustness Certification with General Activation Functions

Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

Evolved Policy Gradients

Learning from Group Comparisons: Exploiting Higher Order Interactions

Hessian-based Analysis of Large Batch Training and Robustness to Adversaries

Bandit Learning with Positive Externalities

Adversarially Robust Generalization Requires More Data

Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents

Learning Confidence Sets using Support Vector Machines

Geometry-Aware Recurrent Neural Networks for Active Visual Recognition

On the Local Minima of the Empirical Risk

Objective and efficient inference for couplings in neuronal networks

Non-Ergodic Alternating Proximal Augmented Lagrangian Algorithms with Optimal Rates

Measures of distortion for machine learning

Is Q-Learning Provably Efficient?

Densely Connected Attention Propagation for Reading Comprehension

Porcupine Neural Networks: Approximating Neural Network Landscapes

Adaptive Negative Curvature Descent with Applications in Non-convex Optimization

Context-dependent upper-confidence bounds for directed exploration

Fast greedy algorithms for dictionary selection with generalized sparsity constraints

Hierarchical Graph Representation Learning with Differentiable Pooling

A Unified View of Piecewise Linear Neural Network Verification

Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

A Smoother Way to Train Structured Prediction Models

Recurrently Controlled Recurrent Networks

Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making

Boolean Decision Rules via Column Generation

Spectral Filtering for General Linear Dynamical Systems

On Learning Intrinsic Rewards for Policy Gradient Methods

Learning filter widths of spectral decompositions with wavelets

Byzantine Stochastic Gradient Descent

Importance Weighting and Variational Inference

Exponentiated Strongly Rayleigh Distributions

Sparsified SGD with Memory

A Mathematical Model For Optimal Decisions In A Representative Democracy

Amortized Inference Regularization

Adaptive Sampling Towards Fast Graph Representation Learning

Semi-Supervised Learning with Declaratively Specified Entropy Constraints

Adversarial Text Generation via Feature-Mover's Distance

Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels

MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare

Active Matting

Limited Memory Kelley's Method Converges for Composite Convex and Submodular Objectives

COLA: Decentralized Linear Learning

Maximum Causal Tsallis Entropy Imitation Learning

Third-order Smoothness Helps: Faster Stochastic Optimization Algorithms for Finding Local Minima

Expanding Holographic Embeddings for Knowledge Completion

Submodular Field Grammars: Representation, Inference, and Application to Image Parsing

Inexact trust-region algorithms on Riemannian manifolds

An Information-Theoretic Analysis for Thompson Sampling with Many Actions

Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates

The Physical Systems Behind Optimization Algorithms

Binary Rating Estimation with Graph Side Information

Completing State Representations using Spectral Learning

Flexible and accurate inference and learning for deep generative models

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

Adding One Neuron Can Eliminate All Bad Local Minima

Differentially Private Uniformly Most Powerful Tests for Binomial Data

Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification

Differentially Private Contextual Linear Bandits

Mean-field theory of graph neural networks in graph partitioning

Can We Gain More from Orthogonality Regularizations in Training Deep Networks?

Scalable Coordinated Exploration in Concurrent Reinforcement Learning

End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems

SimplE Embedding for Link Prediction in Knowledge Graphs

The streaming rollout of deep networks - towards fully model-parallel execution

Beauty-in-averageness and its contextual modulations: A Bayesian statistical account

Differentially Private Robust Low-Rank Approximation

Efficient Projection onto the Perfect Phylogeny Model

A Bridging Framework for Model Optimization and Deep Propagation

Integrated accounts of behavioral and neuroimaging data using flexible recurrent neural network models

GumBolt: Extending Gumbel trick to Boltzmann priors

Bilevel Distance Metric Learning for Robust Image Recognition

Faster Neural Networks Straight from JPEG

BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML Training

Deep Generative Markov State Models

Unsupervised Learning of Object Landmarks through Conditional Image Generation

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

Solving Non-smooth Constrained Programs with Lower Complexity than $\mathcal{O}(1/\varepsilon)$: A Primal-Dual Homotopy Smoothing Approach

Distributed Weight Consolidation: A Brain Segmentation Case Study

Heterogeneous Bitwidth Binarization in Convolutional Neural Networks

Neural Networks Trained to Solve Differential Equations Learn General Representations

KONG: Kernels for ordered-neighborhood graphs

TopRank: A practical algorithm for online stochastic ranking

Early Stopping for Nonparametric Testing

Learning sparse neural networks via sensitivity-driven regularization

Learning from discriminative feature feedback

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans

Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization

Bipartite Stochastic Block Models with Tiny Clusters

Leveraging the Exact Likelihood of Deep Latent Variable Models

Sublinear Time Low-Rank Approximation of Distance Matrices

Minimax Estimation of Neural Net Distance

Lipschitz regularity of deep neural networks: analysis and efficient estimation

Direct Runge-Kutta Discretization Achieves Acceleration

NEON2: Finding Local Minima via First-Order Oracles

Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization

Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting

Convergence of Cubic Regularization for Nonconvex Optimization under KL Property

Variational PDEs for Acceleration on Manifolds and Application to Diffeomorphisms

Equality of Opportunity in Classification: A Causal Approach

DeepProbLog: Neural Probabilistic Logic Programming

Direct Estimation of Differences in Causal Graphs

Inferring Networks From Random Walk-Based Node Similarities

Data center cooling using model-predictive control

Adversarial Attacks on Stochastic Bandits

BinGAN: Learning Compact Binary Descriptors with a Regularized GAN

Escaping Saddle Points in Constrained Optimization

Tight Bounds for Collaborative PAC Learning via Multiplicative Weights

Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization

Bayesian Inference of Temporal Task Specifications from Demonstrations

A Bandit Approach to Sequential Experimental Design with False Discovery Control

Unsupervised Attention-guided Image-to-Image Translation

Neural Code Comprehension: A Learnable Representation of Code Semantics

Optimal Subsampling with Influence Functions

Infinite-Horizon Gaussian Processes

Communication Efficient Parallel Algorithms for Optimization on Manifolds

Multiplicative Weights Updates with Constant Step-Size in Graphical Constant-Sum Games

Hybrid-MST: A Hybrid Active Sampling Strategy for Pairwise Preference Aggregation

Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization

Scaling the Poisson GLM to massive neural datasets through polynomial approximations

Why Is My Classifier Discriminatory?

Actor-Critic Policy Optimization in Partially Observable Multiagent Environments

Multi-Layered Gradient Boosting Decision Trees

Zeroth-order (Non)-Convex Stochastic Optimization via Conditional Gradient and Gradient Updates

Sequence-to-Segment Networks for Segment Detection

Derivative Estimation in Random Design

Boosting Black Box Variational Inference

Latent Gaussian Activity Propagation: Using Smoothness and Structure to Separate and Localize Sounds in Large Noisy Environments

Recurrent Relational Networks

Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals

Step Size Matters in Deep Learning

Modern Neural Networks Generalize on Small Data Sets

Stochastic Spectral and Conjugate Descent Methods

Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds

Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes

Data-Efficient Hierarchical Reinforcement Learning

Inequity aversion improves cooperation in intertemporal social dilemmas

Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibres

Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

Learning to Optimize Tensor Programs

But How Does It Work in Theory? Linear SVM with Random Features

Probabilistic Matrix Factorization for Automated Machine Learning

Training deep learning based denoisers without ground truth data

Re-evaluating evaluation

Learning latent variable structured prediction models with Gaussian perturbations

Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular Reward

Parsimonious Bayesian deep networks

Evidential Deep Learning to Quantify Classification Uncertainty

Speaker-Follower Models for Vision-and-Language Navigation

Asymptotic optimality of adaptive importance sampling

Single-Agent Policy Tree Search With Guarantees

Deep Reinforcement Learning of Marked Temporal Point Processes

On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport

Practical Methods for Graph Two-Sample Testing

The committee machine: Computational to statistical gaps in learning a two-layers neural network

Adaptation to Easy Data in Prediction with Limited Advice

The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal

Semi-crowdsourced Clustering with Deep Generative Models

Q-learning with Nearest Neighbors

Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models

Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization

Differentially Private Bayesian Inference for Exponential Families

Faithful Inversion of Generative Models for Effective Amortized Inference

From Stochastic Planning to Marginal MAP

Optimization over Continuous and Multi-dimensional Decisions with Observational Data

Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces

NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations

When do random forests fail?

Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base

Constructing Deep Neural Networks by Bayesian Network Structure Learning

Fast Estimation of Causal Interactions using Wold Processes

Empirical Risk Minimization Under Fairness Constraints

Optimistic optimization of a Brownian

Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization

Mirrored Langevin Dynamics

Playing hard exploration games by watching YouTube

Weakly Supervised Dense Event Captioning in Videos

Factored Bandits

Gradient Descent Meets Shift-and-Invert Preconditioning for Eigenvector Computation

Norm-Ranging LSH for Maximum Inner Product Search

Analytic solution and stationary phase approximation for the Bayesian lasso and elastic net

Computing Higher Order Derivatives of Matrix and Tensor Expressions

Safe Active Learning for Time-Series Modeling with Gaussian Processes

Contextual bandits with surrogate losses: Margin bounds and efficient algorithms

Demystifying excessively volatile human learning: A Bayesian persistent prior and a neural approximation

Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators

Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering

Natasha 2: Faster Non-Convex Optimization Than SGD

Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes

Paraphrasing Complex Network: Network Compression via Factor Transfer

Optimal Algorithms for Non-Smooth Distributed Optimization in Networks

Processing of missing data by neural networks

Delta-encoder: an effective sample synthesis method for few-shot object recognition

A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication

Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks

Minimax Statistical Learning with Wasserstein distances

Causal Discovery from Discrete Data using Hidden Compact Representation

Online Learning with an Unknown Fairness Metric

Learning Hierarchical Semantic Image Manipulation through Structured Representations

Structural Causal Bandits: Where to Intervene?

Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog

Isolating Sources of Disentanglement in Variational Autoencoders

Representation Balancing MDPs for Off-policy Policy Evaluation

A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation

Provable Variational Inference for Constrained Log-Submodular Models

Representation Learning for Treatment Effect Estimation from Observational Data

Ridge Regression and Provable Deterministic Ridge Leverage Score Sampling

Tree-to-tree Neural Networks for Program Translation

Wasserstein Variational Inference

How Does Batch Normalization Help Optimization?

Verifiable Reinforcement Learning via Policy Extraction

Query Complexity of Bayesian Private Learning

Meta-Gradient Reinforcement Learning

Recurrent World Models Facilitate Policy Evolution

Model Agnostic Supervised Local Explanations

A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization

Learning to Navigate in Cities Without a Map

Gaussian Process Conditional Density Estimation

Local Differential Privacy for Evolving Data

Non-monotone Submodular Maximization in Exponentially Fewer Iterations

MetaGAN: An Adversarial Approach to Few-Shot Learning

Modelling sparsity, heterogeneity, reciprocity and community structure in temporal interaction data

GIANT: Globally Improved Approximate Newton Method for Distributed Optimization

Structured Local Minima in Sparse Blind Deconvolution

Breaking the Span Assumption Yields Fast Finite-Sum Minimization

Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate

BourGAN: Generative Networks with Metric Embeddings

Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning

Revisiting Decomposable Submodular Function Minimization with Incidence Relations

Learning to Reconstruct Shapes from Unseen Classes

Algorithmic Linearly Constrained Gaussian Processes

Mixture Matrix Completion

Smoothed analysis of the low-rank approach for smooth semidefinite programs

One-Shot Unsupervised Cross Domain Translation

Overlapping Clustering Models, and One (class) SVM to Bind Them All

MULAN: A Blind and Off-Grid Method for Multichannel Echo Retrieval

Regularizing by the Variance of the Activations' Sample-Variances

DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning

SplineNets: Continuous Neural Decision Graphs

Trajectory Convolution for Action Recognition

Norm matters: efficient and accurate normalization schemes in deep networks

Learning Optimal Reserve Price against Non-myopic Bidders

Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms

The Description Length of Deep Learning models

Collaborative Learning for Deep Neural Networks

Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning

Automatic Program Synthesis of Long Programs with a Learned Garbage Collector

Generalized Zero-Shot Learning with Deep Calibration Network

Universal Growth in Production Economies

Nonparametric learning from Bayesian models with randomized objective functions

Embedding Logical Queries on Knowledge Graphs

DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors

SEGA: Variance Reduction via Gradient Sketching

Simple random search of static linear policies is competitive for reinforcement learning

A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem

Distributed Stochastic Optimization via Adaptive SGD

Enhancing the Accuracy and Fairness of Human Decision Making

Entropy and mutual information in models of deep neural networks

Deep Attentive Tracking via Reciprocative Learning

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

Bilinear Attention Networks

Pelee: A Real-Time Object Detection System on Mobile Devices

3D-Aware Scene Manipulation via Inverse Graphics

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization

Partially-Supervised Image Captioning

Attention in Convolutional LSTM for Gesture Recognition

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

Virtual Class Enhanced Discriminative Embedding Learning

Temporal Regularization for Markov Decision Process

DifNet: Semantic Segmentation by Diffusion Networks

Variational Memory Encoder-Decoder

Symbolic Graph Reasoning Meets Convolutions

The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning

Efficient Stochastic Gradient Hard Thresholding

Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning

Learning to Exploit Stability for 3D Scene Parsing

High Dimensional Linear Regression using Lattice Basis Reduction

Multi-Class Learning: From Theory to Algorithm

Foreground Clustering for Joint Segmentation and Localization in Videos and Images

PacGAN: The power of two samples in generative adversarial networks

Multivariate Time Series Imputation with Generative Adversarial Networks

Video Prediction via Selective Sampling

Fighting Boredom in Recommender Systems with Linear Reinforcement Learning

Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation

Relating Leverage Scores and Density using Regularized Christoffel Functions

A loss framework for calibrated anomaly detection

Distilled Wasserstein Learning for Word Embedding and Topic Modeling

Non-Local Recurrent Network for Image Restoration

Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners

Genetic-Gated Networks for Deep Reinforcement Learning

Hybrid Knowledge Routed Modules for Large-scale Object Detection

Conditional Adversarial Domain Adaptation

Neural Guided Constraint Logic Programming for Program Synthesis

Learning Versatile Filters for Efficient Convolutional Neural Networks

Designing by Training: Acceleration Neural Network for Fast High-Dimensional Convolution

Gradient Descent for Spiking Neural Networks

Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior

On Oracle-Efficient PAC RL with Rich Observations

SLAYER: Spike Layer Error Reassignment in Time

Generalizing Tree Probability Estimation via Bayesian Networks

Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding

Geometry Based Data Generation

Found Graph Data and Planted Vertex Covers

Adaptive Online Learning in Dynamic Environments

Generative Neural Machine Translation

Multitask Boosting for Survival Analysis with Competing Risks

Toddler-Inspired Visual Object Learning

Alternating optimization of decision trees, with application to learning sparse oblique trees

Unsupervised Learning of View-invariant Action Representations

Interactive Structure Learning with Structural Query-by-Committee

Evolution-Guided Policy Gradient in Reinforcement Learning

Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection

Efficient nonmyopic batch active search

How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD

FRAGE: Frequency-Agnostic Word Representation

Image-to-image translation for cross-domain disentanglement

Boosted Sparse and Low-Rank Tensor Regression

The Lingering of Gradients: How to Reuse Gradients Over Time

$\ell_1$-regression with Heavy-tailed Distributions

Global Geometry of Multichannel Sparse Blind Deconvolution on the Sphere

A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers

Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding

Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making

Quadratic Decomposable Submodular Function Minimization

A Block Coordinate Ascent Algorithm for Mean-Variance Optimization

FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification

Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited

New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity

Reinforced Continual Learning

Learning semantic similarity in a continuous space

Global Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural Networks

MetaReg: Towards Domain Generalization using Meta-Regularization

A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents

Domain-Invariant Projection Learning for Zero-Shot Recognition

Video-to-Video Synthesis

Frequency-Domain Dynamic Pruning for Convolutional Neural Networks

Large Margin Deep Networks for Classification

On the Dimensionality of Word Embedding

Solving Large Sequential Games with the Excessive Gap Technique

Are GANs Created Equal? A Large-Scale Study

DropMax: Adaptive Variational Softmax

Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks

Connectionist Temporal Classification with Maximum Entropy Regularization

KDGAN: Knowledge Distillation with Generative Adversarial Networks

Visual Memory for Robust Path Following

Uncertainty-Aware Attention for Reliable Interpretation and Prediction

Posterior Concentration for Sparse Deep Learning

PointCNN: Convolution On X-Transformed Points

Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN

Do Less, Get More: Streaming Submodular Maximization with Subsampling

A flexible model for training action localization with varying levels of supervision

Deep Neural Nets with Interpolating Function as Output Activation

Long short-term memory and Learning-to-learn in networks of spiking neurons

SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator

TADAM: Task dependent adaptive metric for improved few-shot learning

Generalizing Graph Matching beyond Quadratic Assignment Model

Discrimination-aware Channel Pruning for Deep Neural Networks

A Neural Compositional Paradigm for Image Captioning

Learning Disentangled Joint Continuous and Discrete Representations

FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction

Informative Features for Model Comparison

A Unified Framework for Extensive-Form Game Abstraction with Bounds

Quantifying Learning Guarantees for Convex but Inconsistent Surrogates

Removing the Feature Correlation Effect of Multiplicative Noise

Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients?

Dialog-based Interactive Image Retrieval

Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives

HitNet: Hybrid Ternary Recurrent Neural Network

How to Start Training: The Effect of Initialization and Architecture

LinkNet: Relational Embedding for Scene Graph

Self-Erasing Network for Integral Object Attention

Multi-Task Learning as Multi-Objective Optimization

A Model for Learned Bloom Filters and Optimizing by Sandwiching

Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search

Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal Modeling

On Misinformation Containment in Online Social Networks

(Probably) Concave Graph Matching

Implicit Reparameterization Gradients

Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes

PAC-learning in the presence of adversaries

Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis

Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions

Learning Deep Disentangled Embeddings With the F-Statistic Loss

Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced

Learning to Decompose and Disentangle Representations for Video Prediction

Chain of Reasoning for Visual Question Answering

Sparse DNNs with Improved Adversarial Robustness

Optimization for Approximate Submodularity

An Efficient Pruning Algorithm for Robust Isotonic Regression

Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation

Self-Supervised Generation of Spatial Audio for 360° Video

Training DNNs with Hybrid Block Floating Point

Deep Defense: Training DNNs with Improved Adversarial Robustness

Snap ML: A Hierarchical Framework for Machine Learning

Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC

Sigsoftmax: Reanalysis of the Softmax Bottleneck

Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units

A^2-Nets: Double Attention Networks

Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation

How Many Samples are Needed to Estimate a Convolutional Neural Network?

Fast Similarity Search via Optimal Sparse Lifting

Supervised autoencoders: Improving generalization performance with unsupervised regularizers

Geometrically Coupled Monte Carlo Sampling

Generalized Inverse Optimization through Online Learning

Image Inpainting via Generative Multi-column Convolutional Neural Networks

Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems

Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning

MetaAnchor: Learning to Detect Objects with Customized Anchors

Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution

Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language

HOGWILD!-Gibbs can be PanAccurate

IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis

An Off-policy Policy Gradient Theorem Using Emphatic Weightings

See and Think: Disentangling Semantic Scene Completion

Visual Object Networks: Image Generation with Disentangled 3D Representations

Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization

Structure-Aware Convolutional Neural Networks

Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with $\beta$-Divergences

Learning long-range spatial dependencies with horizontal gated recurrent units

Kalman Normalization: Normalizing Internal Representations Across Network Layers