International Conference on Learning Representations (ICLR) - 2019

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation 2
A Closer Look at Few-shot Classification 4
A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks 2
A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery 4
A Direct Approach to Robust Deep Learning Using Adversarial Networks 4
A Generative Model For Electron Paths 5
A Kernel Random Matrix-Based Approach for Sparse PCA 3
A Max-Affine Spline Perspective of Recurrent Neural Networks 3
A Mean Field Theory of Batch Normalization 2
A Statistical Approach to Assessing Neural Network Robustness 4
A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs 3
A Universal Music Translation Network 3
A Variational Inequality Perspective on Generative Adversarial Networks 6
A comprehensive, application-oriented study of catastrophic forgetting in DNNs 6
A new dog learns old tricks: RL finds classic optimization algorithms 1
A rotation-equivariant convolutional neural network model of primary visual cortex 4
A2BCD: Asynchronous Acceleration with Optimal Complexity 5
ACCELERATING NONCONVEX LEARNING VIA REPLICA EXCHANGE LANGEVIN DIFFUSION 0
AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active Tracking 3
ADef: an Iterative Algorithm to Construct Adversarial Deformations 5
ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA 6
ANYTIME MINIBATCH: EXPLOITING STRAGGLERS IN ONLINE DISTRIBUTED OPTIMIZATION 4
ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary Networks 6
Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks 3
Active Learning with Partial Feedback 4
AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods 4
Adaptive Estimators Show Information Compression in Deep Neural Networks 2
Adaptive Gradient Methods with Dynamic Bound of Learning Rate 4
Adaptive Input Representations for Neural Language Modeling 5
Adaptive Posterior Learning: few-shot learning with a surprise-based memory module 3
Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality 0
Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network 4
Adversarial Attacks on Graph Neural Networks via Meta Learning 3
Adversarial Audio Synthesis 6
Adversarial Domain Adaptation for Stable Brain-Machine Interfaces 2
Adversarial Imitation via Variational Inverse Reinforcement Learning 4
Adversarial Reprogramming of Neural Networks 3
Aggregated Momentum: Stability Through Passive Damping 3
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees 5
Amortized Bayesian Meta-Learning 4
An Empirical Study of Example Forgetting during Deep Neural Network Learning 5
An Empirical study of Binary Neural Networks' Optimisation 4
An analytic theory of generalization dynamics and transfer learning in deep linear networks 0
Analysing Mathematical Reasoning Abilities of Neural Models 4
Analysis of Quantized Models 4
Analyzing Inverse Problems with Invertible Neural Networks 1
AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks 3
Approximability of Discriminators Implies Diversity in GANs 3
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet 4
Are adversarial examples inevitable? 3
Attention, Learn to Solve Routing Problems! 5
Attentive Neural Processes 4
Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation 3
AutoLoss: Learning Discrete Schedule for Alternate Optimization 4
Automatically Composing Representation Transformations as a Means for Generalization 4
Auxiliary Variational MCMC 6
BA-Net: Dense Bundle Adjustment Networks 2
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning 3
Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity 3
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes 3
Bayesian Policy Optimization for Model Uncertainty 3
Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods 3
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations 4
Beyond Greedy Ranking: Slate Optimization via List-CVAE 2
Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer 5
Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers 4
Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition 4
Biologically-Plausible Learning Algorithms Can Scale to Large Datasets 5
Boosting Robustness Certification of Neural Networks 5
Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces 4
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension 4
CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild 4
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model 4
CEM-RL: Combining evolutionary and gradient-based methods for policy search 4
Capsule Graph Neural Network 4
Caveats for information bottleneck in deterministic scenarios 4
Characterizing Audio Adversarial Examples Using Temporal Dependency 2
ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech 3
Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering 3
Combinatorial Attacks on Binarized Neural Networks 4
Competitive experience replay 3
Complement Objective Training 6
Composing Complex Skills by Learning Transition Policies 3
Conditional Network Embeddings 5
Context-adaptive Entropy Model for End-to-end Optimized Image Compression 4
Contingency-Aware Exploration in Reinforcement Learning 3
Convolutional Neural Networks on Non-uniform Geometrical Signals Using Euclidean Spectral Transformation 2
Cost-Sensitive Robustness against Adversarial Examples 4
Critical Learning Periods in Deep Networks 2
DARTS: Differentiable Architecture Search 6
DELTA: DEEP LEARNING TRANSFER USING FEATURE MAP WITH ATTENTION FOR CONVOLUTIONAL NETWORKS 3
DHER: Hindsight Experience Replay for Dynamic Goals 4
DISTRIBUTIONAL CONCAVITY REGULARIZATION FOR GANS 3
DOM-Q-NET: Grounded RL on Structured Language 4
DPSNet: End-to-end Deep Plane Sweep Stereo 3
Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds 4
Decoupled Weight Decay Regularization 4
Deep Anomaly Detection with Outlier Exposure 4
Deep Convolutional Networks as shallow Gaussian Processes 6
Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks 3
Deep Frank-Wolfe For Neural Network Optimization 6
Deep Graph Infomax 4
Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning 2
Deep Layers as Stochastic Solvers 3
Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere Convolution 2
Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL 2
Deep learning generalizes because the parameter-function map is biased towards simple functions 2
Deep reinforcement learning with relational inductive biases 1
Deep, Skinny Neural Networks are not Universal Approximators 1
DeepOBS: A Deep Learning Optimizer Benchmark Suite 5
Defensive Quantization: When Efficiency Meets Robustness 3
Detecting Egregious Responses in Neural Sequence-to-sequence Models 4
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience 2
Deterministic Variational Inference for Robust Bayesian Neural Networks 4
Diagnosing and Enhancing VAE Models 2
DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder 5
Differentiable Learning-to-Normalize via Switchable Normalization 5
Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder 5
Diffusion Scattering Transforms on Graphs 1
Dimensionality Reduction for Representing the Knowledge of Probabilistic Models 5
Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information 2
Discovery of Natural Language Concepts in Individual Units of CNNs 4
Discriminator Rejection Sampling 4
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning 4
Disjoint Mapping Network for Cross-modal Matching of Voices and Faces 4
Distribution-Interpolation Trade off in Generative Models 2
Diversity and Depth in Per-Example Routing Models 3
Diversity is All You Need: Learning Skills without a Reward Function 4
Diversity-Sensitive Conditional Generative Adversarial Networks 3
Do Deep Generative Models Know What They Don't Know? 2
Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors 5
Don't let your Discriminator be fooled 2
Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network 4
Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives 4
DyRep: Learning Representations over Dynamic Graphs 3
Dynamic Channel Pruning: Feature Boosting and Suppression 4
Dynamic Sparse Graph for Efficient Deep Learning 4
Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration 3
Efficient Augmentation via Data Subsampling 5
Efficient Lifelong Learning with A-GEM 5
Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution 5
Efficient Training on Very Large Corpora via Gramian Estimation 4
Efficiently testing local optimality and escaping saddles for ReLU networks 3
Eidetic 3D LSTM: A Model for Video Prediction and Beyond 4
Emergent Coordination Through Competition 4
Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer 2
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset 3
Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking 5
Environment Probing Interaction Policies 4
Episodic Curiosity through Reachability 4
Equi-normalization of Neural Networks 6
Evaluating Robustness of Neural Networks with Mixed Integer Programming 6
Excessive Invariance Causes Adversarial Vulnerability 4
Execution-Guided Neural Program Synthesis 4
Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency 2
Explaining Image Classifiers by Counterfactual Generation 5
Exploration by random network distillation 3
FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models 4
FUNCTIONAL VARIATIONAL BAYESIAN NEURAL NETWORKS 4
Feature Intertwiner for Object Detection 6
Feature-Wise Bias Amplification 2
Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers 4
Fixup Initialization: Residual Learning Without Normalization 3
FlowQA: Grasping Flow in History for Conversational Machine Comprehension 4
Fluctuation-dissipation relations for stochastic gradient descent 2
From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference 2
From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following 4
Function Space Particle Optimization for Bayesian Neural Networks 5
G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space 6
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks 1
GANSynth: Adversarial Neural Audio Synthesis 5
GENERATING HIGH FIDELITY IMAGES WITH SUBSCALE PIXEL NETWORKS AND MULTIDIMENSIONAL UPSCALING 3
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding 4
GO Gradient for Expectation-Based Objectives 6
GamePad: A Learning Environment for Theorem Proving 4
Generalizable Adversarial Training via Spectral Normalization 5
Generalized Tensor Models for Recurrent Neural Networks 2
Generating Liquid Simulations with Deformation-aware Neural Networks 4
Generating Multi-Agent Trajectories using Programmatic Weak Supervision 4
Generating Multiple Objects at Spatially Distinct Locations 4
Generative Code Modeling with Graphs 4
Generative Question Answering: Learning to Answer the Whole Question 3
Generative predecessor models for sample-efficient imitation learning 2
Global-to-local Memory Pointer Networks for Task-Oriented Dialogue 4
Gradient Descent Provably Optimizes Over-parameterized Neural Networks 0
Gradient descent aligns the layers of deep linear networks 2
Graph HyperNetworks for Neural Architecture Search 3
Graph Wavelet Neural Network 3
Guiding Policies with Language via Meta-Learning 2
Harmonic Unpaired Image-to-image Translation 3
Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation 3
Hierarchical Generative Modeling for Controllable Speech Synthesis 2
Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies 3
Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization 4
Hierarchical Visuomotor Control of Humanoids 3
Hierarchical interpretations for neural network predictions 3
Hindsight policy gradients 4
How Important is a Neuron 3
How Powerful are Graph Neural Networks? 4
How to train your MAML 3
Human-level Protein Localization with Convolutional Neural Networks 5
Hyperbolic Attention Networks 3
INVASE: Instance-wise Variable Selection using Neural Networks 5
Identifying and Controlling Important Neurons in Neural Machine Translation 3
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness 6
Imposing Category Trees Onto Word-Embeddings Using A Geometric Construction 4
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control 4
Improving Generalization and Stability of Generative Adversarial Networks 4
Improving MMD-GAN Training with Repulsive Loss Function 3
Improving Sequence-to-Sequence Learning via Optimal Transport 6
Improving the Generalization of Adversarial Training with Domain Adaptation 5
InfoBot: Transfer and Exploration via the Information Bottleneck 4
Information Theoretic lower bounds on negative log likelihood 3
Information asymmetry in KL-regularized RL 2
Information-Directed Exploration for Deep Reinforcement Learning 4
Initialized Equilibrium Propagation for Backprop-Free Training 4
InstaGAN: Instance-aware Image-to-Image Translation 3
Integer Networks for Data Compression with Latent-Variable Models 2
Interpolation-Prediction Networks for Irregularly Sampled Time Series 4
Invariant and Equivariant Graph Networks 3
Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs 4
K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning 3
Kernel Change-point Detection with Auxiliary Deep Generative Models 6
Kernel RNN Learning (KeRNL) 3
KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks 2
Knowledge Flow: Improve Upon Your Teachers 3
L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data 4
L2-Nonexpansive Neural Networks 4
LEARNING FACTORIZED REPRESENTATIONS FOR OPEN-SET DOMAIN ADAPTATION 4
LEARNING TO PROPAGATE LABELS: TRANSDUCTIVE PROPAGATION NETWORK FOR FEW-SHOT LEARNING 3
Label super-resolution networks 3
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders 5
LanczosNet: Multi-Scale Deep Graph Convolutional Networks 5
Large Scale GAN Training for High Fidelity Natural Image Synthesis 5
Large Scale Graph Learning From Smooth Signals 4
Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation 5
Large-Scale Study of Curiosity-Driven Learning 4
Latent Convolutional Models 3
LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators 2
LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos 4
Learnable Embedding Space for Efficient Neural Architecture Compression 4
Learning Actionable Representations with Goal Conditioned Policies 2
Learning Embeddings into Entropic Wasserstein Spaces 2
Learning Exploration Policies for Navigation 2
Learning Factorized Multimodal Representations 3
Learning Finite State Representations of Recurrent Policy Networks 3
Learning Grid Cells as Vector Representation of Self-Position Coupled with Matrix Representation of Self-Motion 2
Learning Implicitly Recurrent CNNs Through Parameter Sharing 5
Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional Clustering 3
Learning Localized Generative Models for 3D Point Clouds via Graph Convolution 3
Learning Mixed-Curvature Representations in Product Spaces 3
Learning Multi-Level Hierarchies with Hindsight 4
Learning Multimodal Graph-to-Graph Translation for Molecule Optimization 4
Learning Neural PDE Solvers with Convergence Guarantees 2
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids 4
Learning Procedural Abstractions and Evaluating Discrete Latent Temporal Structure 4
Learning Programmatically Structured Representations with Perceptor Gradients 2
Learning Protein Structure with a Differentiable Simulator 5
Learning Recurrent Binary/Ternary Weights 5
Learning Representations of Sets through Optimized Permutations 5
Learning Robust Representations by Projecting Superficial Statistics Out 3
Learning Self-Imitating Diverse Policies 3
Learning To Simulate 4
Learning To Solve Circuit-SAT: An Unsupervised Differentiable Approach 1
Learning Two-layer Neural Networks with Symmetric Inputs 1
Learning a Meta-Solver for Syntax-Guided Program Synthesis 4
Learning a SAT Solver from Single-Bit Supervision 1
Learning concise representations for regression by evolving networks of trees 4
Learning deep representations by mutual information estimation and maximization 3
Learning from Positive and Unlabeled Data with a Selection Bias 5
Learning protein sequence embeddings using information from structure 5
Learning sparse relational transition models 3
Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning 3
Learning to Describe Scenes with Programs 4
Learning to Design RNA 7
Learning to Infer and Execute 3D Shape Programs 4
Learning to Learn with Conditional Class Dependencies 3
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference 5
Learning to Make Analogies by Contrasting Abstract Relational Structure 3
Learning to Navigate the Web 3
Learning to Remember More with Less Memorization 4
Learning to Represent Edits 4
Learning to Schedule Communication in Multi-agent Reinforcement Learning 4
Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks 4
Learning to Understand Goal Specifications by Modelling Reward 2
Learning what and where to attend 5
Learning what you can do before doing anything 3
Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks 3
Learning-Based Frequency Estimation Algorithms 4
Local SGD Converges Fast and Communicates Little 4
MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders 2
MARGINALIZED AVERAGE ATTENTIONAL NETWORK FOR WEAKLY-SUPERVISED LEARNING 5
M^3RL: Mind-aware Multi-agent Management Reinforcement Learning 3
Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications 2
Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds 2
Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability Detection 5
Measuring Compositionality in Representation Learning 4
Measuring and regularizing networks in function space 4
Meta-Learning For Stochastic Gradient MCMC 4
Meta-Learning Probabilistic Inference for Prediction 5
Meta-Learning Update Rules for Unsupervised Representation Learning 5
Meta-Learning with Latent Embedding Optimization 5
Meta-learning with differentiable closed-form solvers 5
Minimal Images in Deep Neural Networks: Fragile Object Recognition in Natural Images 3
Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters 5
Minimum Divergence vs. Maximum Margin: an Empirical Comparison on Seq2Seq Models 4
MisGAN: Learning from Incomplete Data with Generative Adversarial Networks 3
Mode Normalization 6
Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic 4
Modeling Uncertainty with Hedged Instance Embeddings 2
Modeling the Long Term Future in Model-Based Reinforcement Learning 3
Multi-Agent Dual Learning 5
Multi-Domain Adversarial Learning 4
Multi-class classification without multi-class labels 3
Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering 5
Multilingual Neural Machine Translation With Soft Decoupled Encoding 4
Multilingual Neural Machine Translation with Knowledge Distillation 5
Multiple-Attribute Text Rewriting 2
Music Transformer: Generating Music with Long-Term Structure 3
NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning 2
NOODL: Provable Online Dictionary Learning and Sparse Coding 4
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning 4
Neural Graph Evolution: Towards Efficient Automatic Robot Design 3
Neural Logic Machines 3
Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology 5
Neural Probabilistic Motor Primitives for Humanoid Control 3
Neural Program Repair by Jointly Learning to Localize and Repair 2
Neural Speed Reading with Structural-Jump-LSTM 4
Neural TTS Stylization with Adversarial and Collaborative Games 1
Neural network gradient-based learning of black-box function interfaces 2
No Training Required: Exploring Random Encoders for Sentence Classification 4
Non-vacuous Generalization Bounds at the ImageNet Scale: a PAC-Bayesian Compression Approach 3
Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy 3
On Computation and Generalization of Generative Adversarial Networks under Spectrum Control 3
On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training 2
On Self Modulation for Generative Adversarial Networks 4
On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization 3
On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data 3
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length 3
On the Sensitivity of Adversarial Robustness to Input Data Distributions 2
On the Turing Completeness of Modern Neural Network Architectures 0
On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks 0
On the loss landscape of a class of deep neural networks with no bad local valleys 2
Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams 5
Optimal Completion Distillation for Sequence Learning 4
Optimal Control Via Neural Networks: A Convex Approach 2
Optimal Transport Maps For Distribution Preserving Operations on Latent Spaces of Generative Models 3
Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile 3
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks 4
Overcoming Catastrophic Forgetting for Continual Learning via Model Adaptation 5
Overcoming the Disentanglement vs Reconstruction Trade-off via Jacobian Supervision 4
PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees 3
Pay Less Attention with Lightweight and Dynamic Convolutions 5
PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks 2
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm 3
Phase-Aware Speech Enhancement with Deep Complex U-Net 3
Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control 3
Poincare Glove: Hyperbolic Word Embeddings 5
Policy Transfer with Strategy Optimization 2
Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator 3
Posterior Attention Models for Sequence to Sequence Learning 2
Practical lossless compression with latent variables using bits back coding 4
Preconditioner on Matrix Lie Group for SGD 4
Predict then Propagate: Graph Neural Networks meet Personalized PageRank 4
Predicting the Generalization Gap in Deep Networks with Margin Distributions 4
Preferences Implicit in the State of the World 3
Preventing Posterior Collapse with delta-VAEs 3
Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors 5
ProMP: Proximal Meta-Policy Search 4
ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees 3
Probabilistic Planning with Sequential Monte Carlo methods 3
Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning 3
ProxQuant: Quantized Neural Networks via Proximal Operators 5
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware 5
Quasi-hyperbolic momentum and Adam for deep learning 6
Quaternion Recurrent Neural Networks 5
Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach 5
RNNs implicitly implement tensor-product representations 4
ROBUST ESTIMATION VIA GENERATIVE ADVERSARIAL NETWORKS 3
Random mesh projectors for inverse problems 2
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning 2
Recall Traces: Backtracking Models for Efficient Reinforcement Learning 3
Recurrent Experience Replay in Distributed Reinforcement Learning 2
Regularized Learning for Domain Adaptation under Label Shifts 3
RelGAN: Relational Generative Adversarial Networks for Text Generation 4
Relational Forward Models for Multi-Agent Learning 2
Relaxed Quantization for Discretized Neural Networks 6
Representation Degeneration Problem in Training Natural Language Generation Models 3
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks 1
Residual Non-local Attention Networks for Image Restoration 3
Rethinking the Value of Network Pruning 4
Revealing interpretable object representations from human behavior 2
Reward Constrained Policy Optimization 2
Riemannian Adaptive Optimization Methods 4
Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures 2
Robust Conditional Generative Adversarial Networks 2
Robustness May Be at Odds with Accuracy 3
RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks 3
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space 4
SGD Converges to Global Minimum in Deep Learning via Star-convex Path 2
SNAS: stochastic neural architecture search 4
SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY 5
SOM-VAE: Interpretable Discrete Representation Learning on Time Series 3
SPIGAN: Privileged Adversarial Learning from Simulation 3
STCN: Stochastic Temporal Convolutional Networks 5
Sample Efficient Adaptive Text-to-Speech 3
Sample Efficient Imitation Learning for Continuous Control 4
Scalable Unbalanced Optimal Transport using Generative Adversarial Networks 3
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation 4
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions 5
Selfless Sequential Learning 2
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware 6
Sliced Wasserstein Auto-Encoders 4
Slimmable Neural Networks 6
Small nonlinearities in activation functions create bad local minima in neural networks 0
Smoothing the Geometry of Probabilistic Box Embeddings 3
Soft Q-Learning with Mutual-Information Regularization 3
Solving the Rubik's Cube with Approximate Policy Iteration 2
Sparse Dictionary Learning by Dynamical Neural Networks 3
Spectral Inference Networks: Unifying Deep and Spectral Learning 4
Spherical CNNs on Unstructured Grids 5
Spreading vectors for similarity search 5
Stable Opponent Shaping in Differentiable Games 2
Stable Recurrent Models 2
Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization 0
Stochastic Optimization of Sorting Networks via Continuous Relaxations 5
Stochastic Prediction of Multi-Agent Interactions from Partial Observations 4
StrokeNet: A Neural Painting Environment 4
Structured Adversarial Attack: Towards General Implementation and Better Interpretability 5
Structured Neural Summarization 5
Subgradient Descent Learns Orthogonal Dictionaries 2
Supervised Community Detection with Line Graph Neural Networks 3
Supervised Policy Update for Deep Reinforcement Learning 4
Synthetic Datasets for Neural Program Synthesis 1
Systematic Generalization: What Is Required and Can It Be Learned? 5
Temporal Difference Variational Auto-Encoder 2
The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent Structure 1
The Deep Weight Prior 4
The Laplacian in RL: Learning Representations with Efficient Approximations 1
The Limitations of Adversarial Training and the Blind-Spot Attack 2
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks 4
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision 5
The Singular Values of Convolutional Layers 3
The Unusual Effectiveness of Averaging in GAN Training 3
The relativistic discriminator: a key element missing from standard GAN 4
The role of over-parametrization in generalization of neural networks 2
Theoretical Analysis of Auto Rate-Tuning by Batch Normalization 2
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average 4
Three Mechanisms of Weight Decay Regularization 4
TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer 3
Time-Agnostic Prediction: Predicting Predictable Video Frames 3
Top-Down Neural Model For Formulae 3
Toward Understanding the Impact of Staleness in Distributed Machine Learning 2
Towards GAN Benchmarks Which Require Generalization 3
Towards Metamerism via Foveated Style Transfer 4
Towards Robust, Locally Linear Deep Networks 3
Towards Understanding Regularization in Batch Normalization 2
Towards the first adversarially robust neural network model on MNIST 3
Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability 5
Transfer Learning for Sequences via Learning to Collocate 4
Transferring Knowledge across Learning Processes 4
Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale Modeling 3
Trellis Networks for Sequence Modeling 4
Two-Timescale Networks for Nonlinear Value Function Approximation 3
Understanding Composition of Word Embeddings via Tensor Decomposition 4
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets 4
Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer 3
Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutions 3
Universal Successor Features Approximators 3
Universal Transformers 6
Unsupervised Adversarial Image Reconstruction 4
Unsupervised Control Through Non-Parametric Discriminative Rewards 3
Unsupervised Discovery of Parts, Structure, and Dynamics 3
Unsupervised Domain Adaptation for Distance Metric Learning 3
Unsupervised Hyper-alignment for Multilingual Word Embeddings 2
Unsupervised Learning of the Set of Local Maxima 3
Unsupervised Learning via Meta-Learning 5
Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching 4
Value Propagation Networks 2
Variance Networks: When Expectation Does Not Meet Your Expectations 3
Variance Reduction for Reinforcement Learning in Input-Driven Environments 4
Variational Autoencoder with Arbitrary Conditioning 4
Variational Autoencoders with Jointly Optimized Latent Dependency Structure 3
Variational Bayesian Phylogenetic Inference 4
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow 5
Variational Smoothing in Recurrent Neural Network Language Models 2
Verification of Non-Linear Specifications for Neural Networks 2
Visceral Machines: Risk-Aversion in Reinforcement Learning with Intrinsic Physiological Rewards 1
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks 4
Visual Reasoning by Progressive Module Networks 4
Visual Semantic Navigation using Scene Priors 4
Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs 6
Wasserstein Barycenter Model Ensembling 5
What do you learn from context? Probing for sentence structure in contextualized word representations 4
Whitening and Coloring Batch Transform for GANs 4
Wizard of Wikipedia: Knowledge-Powered Conversational Agents 4
Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search 2
code2seq: Generating Sequences from Structured Representations of Code 4
h-detach: Modifying the LSTM Gradient Towards Better Optimization 5
signSGD via Zeroth-Order Oracle 3
signSGD with Majority Vote is Communication Efficient and Fault Tolerant 4
textTOvec: DEEP CONTEXTUALIZED NEURAL AUTOREGRESSIVE TOPIC MODELS OF LANGUAGE WITH DISTRIBUTED COMPOSITIONAL PRIOR 5