International Conference on Learning Representations (ICLR) - 2020

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 Baseline for Few-Shot Image Classification 4
A Closer Look at Deep Policy Gradients 3
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks 3
A Constructive Prediction of the Generalization Error Across Scales 3
A FRAMEWORK FOR ROBUSTNESS CERTIFICATION OF SMOOTHED CLASSIFIERS USING F-DIVERGENCES 3
A Fair Comparison of Graph Neural Networks for Graph Classification 5
A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case 0
A Generalized Training Approach for Multiagent Learning 3
A Latent Morphology Model for Open-Vocabulary Neural Machine Translation 5
A Learning-based Iterative Method for Solving Vehicle Routing Problems 3
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms 4
A Mutual Information Maximization Perspective of Language Representation Learning 3
A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning 3
A Probabilistic Formulation of Unsupervised Text Style Transfer 4
A Signal Propagation Perspective for Pruning Neural Networks at Initialization 4
A Stochastic Derivative Free Optimization Method with Momentum 4
A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learning 6
A Theoretical Analysis of the Number of Shots in Few-Shot Learning 4
A Theory of Usable Information under Computational Constraints 3
A closer look at the approximation capabilities of neural networks 0
A critical analysis of self-supervision, or what we can learn from a single image 4
AE-OT: A NEW GENERATIVE MODEL BASED ON EXTENDED SEMI-DISCRETE OPTIMAL TRANSPORT 3
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations 5
AMRL: Aggregated Memory For Reinforcement Learning 2
Abductive Commonsense Reasoning 4
Abstract Diagrammatic Reasoning with Multiplex Graph Networks 4
Accelerating SGD with momentum for over-parameterized learning 4
Action Semantics Network: Considering the Effects of Actions in Multiagent Systems 3
Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games 1
Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation 5
Adaptive Structural Fingerprints for Graph Attention Networks 4
Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks 5
Adjustable Real-time Style Transfer 4
AdvectiveNet: An Eulerian-Lagrangian Fluidic Reservoir for Point Cloud Processing 5
Adversarial AutoAugment 5
Adversarial Lipschitz Regularization 3
Adversarial Policies: Attacking Deep Reinforcement Learning 4
Adversarial Training and Provable Defenses: Bridging the Gap 7
Adversarially Robust Representations with Smooth Encoders 3
Adversarially robust transfer learning 4
An Exponential Learning Rate Schedule for Deep Learning 2
An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality 4
Analysis of Video Feature Learning in Two-Stream CNNs on the Example of Zebrafish Swim Bout Classification 6
And the Bit Goes Down: Revisiting the Quantization of Neural Networks 5
Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction 5
Are Transformers universal approximators of sequence-to-sequence functions? 4
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures 4
Asymptotics of Wide Networks from Feynman Diagrams 2
At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? 2
AtomNAS: Fine-Grained End-to-End Neural Architecture Search 6
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty 4
Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space 3
Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History 3
AutoQ: Automated Kernel-Wise Neural Network Quantization 3
Automated Relational Meta-learning 4
Automated curriculum generation through setter-solver interactions 3
Automatically Discovering and Learning New Visual Categories with Ranking Statistics 6
B-Spline CNNs on Lie groups 3
BERTScore: Evaluating Text Generation with BERT 5
BREAKING CERTIFIED DEFENSES: SEMANTIC ADVERSARIAL EXAMPLES WITH SPOOFED ROBUSTNESS CERTIFICATES 3
BackPACK: Packing more into Backprop 4
Batch-shaping for learning conditional channel gated networks 5
BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong Learning 4
BayesOpt Adversarial Attack 4
Bayesian Meta Sampling for Fast Uncertainty Adaptation 5
Behaviour Suite for Reinforcement Learning 3
Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks 0
BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations 5
Biologically inspired sleep algorithm for increased generalization and adversarial robustness in deep neural networks 3
Black-Box Adversarial Attack with Transferable Model-based Embedding 6
Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning 3
BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget 5
Bounds on Over-Parameterization for Guaranteed Existence of Descent Paths in Shallow ReLU Networks 0
Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness 5
Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints 4
Building Deep Equivariant Capsule Networks 4
CAQL: Continuous Action Q-Learning 4
CATER: A diagnostic dataset for Compositional Actions & TEmporal Reasoning 4
CLEVRER: Collision Events for Video Representation and Reasoning 3
CLN2INV: Learning Loop Invariants with Continuous Logic Networks 5
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning 4
Can gradient clipping mitigate label noise? 3
Capsules with Inverted Dot-Product Attention Routing 4
Causal Discovery with Reinforcement Learning 3
Certified Defenses for Adversarial Patches 4
Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing 4
Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation 5
Classification-Based Anomaly Detection for General Data 4
Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring in Data 3
CoPhy: Counterfactual Learning of Physical Dynamics 3
Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization 2
Combining Q-Learning and Search with Amortized Value Estimates 5
Comparing Rewinding and Fine-tuning in Neural Network Pruning 6
Composing Task-Agnostic Policies with Deep Reinforcement Learning 3
Composition-based Multi-Relational Graph Convolutional Networks 4
Compositional Language Continual Learning 4
Compositional languages emerge in a neural iterated learning model 4
Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network 2
Compressive Transformers for Long-Range Sequence Modelling 6
Computation Reallocation for Object Detection 5
Conditional Learning of Fair Representations 3
Conservative Uncertainty Estimation By Fitting Prior Networks 3
Consistency Regularization for Generative Adversarial Networks 5
Continual Learning with Adaptive Weights (CLAW) 4
Continual Learning with Bayesian Neural Networks for Non-Stationary Data 3
Continual learning with hypernetworks 4
Contrastive Learning of Structured World Models 4
Contrastive Representation Distillation 5
Controlling generative models with continuous factors of variations 5
Convergence of Gradient Methods on Bilinear Zero-Sum Games 1
Convolutional Conditional Neural Processes 4
Counterfactuals uncover the modular structure of deep generative models 3
Critical initialisation in continuous approximations of binary neural networks 2
Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation 5
Cross-Lingual Ability of Multilingual BERT: An Empirical Study 4
Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework 4
Curriculum Loss: Robust Learning and Generalization against Label Corruption 3
Curvature Graph Network 4
Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning 4
DBA: Distributed Backdoor Attacks against Federated Learning 3
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames 7
DDSP: Differentiable Digital Signal Processing 3
Data-Independent Neural Pruning via Coresets 5
Data-dependent Gaussian Prior Objective for Language Generation 3
DeFINE: Deep Factorized Input Token Embeddings for Neural Sequence Modeling 5
Decentralized Deep Learning with Arbitrary Communication Compression 6
Decoding As Dynamic Programming For Recurrent Autoregressive Models 3
Decoupling Representation and Classifier for Long-Tailed Recognition 4
Deep 3D Pan via local adaptive "t-shaped" convolutions with global and local adaptive dilations 3
Deep Audio Priors Emerge From Harmonic Convolutional Networks 4
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds 4
Deep Double Descent: Where Bigger Models and More Data Hurt 3
Deep Graph Matching Consensus 5
Deep Imitative Models for Flexible Inference, Planning, and Control 3
Deep Learning For Symbolic Mathematics 3
Deep Learning of Determinantal Point Processes via Proper Spectral Sub-gradient 5
Deep Network Classification by Scattering and Homotopy Dictionary Learning 4
Deep Orientation Uncertainty Learning based on a Bingham Loss 4
Deep Semi-Supervised Anomaly Detection 5
Deep Symbolic Superoptimization Without Human Knowledge 5
Deep neuroethology of a virtual rodent 3
Deep probabilistic subsampling for task-adaptive compressed sensing 5
DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures 5
DeepSphere: a graph-based spherical CNN 3
DeepV2D: Video to Depth with Differentiable Structure from Motion 4
Defending Against Physically Realizable Attacks on Image Classification 5
Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation 3
Demystifying Inter-Class Disentanglement 3
Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators 3
Depth-Adaptive Transformer 4
Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem 1
Detecting Extrapolation with Local Ensembles 5
Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions 3
DiffTaichi: Differentiable Programming for Physical Simulation 4
Difference-Seeking Generative Adversarial Network--Unseen Sample Generation 4
Differentiable Reasoning over a Virtual Knowledge Base 5
Differentiable learning of numerical rules in knowledge graphs 4
Differentially Private Meta-Learning 4
Differentiation of Blackbox Combinatorial Solvers 4
Directional Message Passing for Molecular Graphs 4
Disagreement-Regularized Imitation Learning 2
Discovering Motor Programs by Recomposing Demonstrations 3
Discrepancy Ratio: Evaluating Model Performance When Even Experts Disagree on the Truth 3
Discriminative Particle Filter Reinforcement Learning for Complex Partial observations 7
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN) 2
Disentangling Factors of Variations Using Few Labels 4
Disentangling neural mechanisms for perceptual grouping 3
Distance-Based Learning from Errors for Confidence Calibration 3
Distributed Bandit Learning: Near-Optimal Regret with Efficient Communication 1
Distributionally Robust Neural Networks 5
Diverse Trajectory Forecasting with Determinantal Point Processes 3
DivideMix: Learning with Noisy Labels as Semi-supervised Learning 6
Domain Adaptive Multibranch Networks 3
Don't Use Large Mini-batches, Use Local SGD 6
Double Neural Counterfactual Regret Minimization 4
Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation 3
Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks 5
Dream to Control: Learning Behaviors by Latent Imagination 5
DropEdge: Towards Deep Graph Convolutional Networks on Node Classification 5
Duration-of-Stay Storage Assignment under Uncertainty 5
Dynamic Model Pruning with Feedback 5
Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers 2
Dynamic Time Lag Regression: Predicting What & When 4
Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery 3
Dynamically Pruned Message Passing Networks for Large-scale Knowledge Graph Reasoning 6
Dynamics-Aware Embeddings 2
Dynamics-Aware Unsupervised Discovery of Skills 4
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators 4
EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness Against Adversarial Attacks 3
ES-MAML: Simple Hessian-Free Meta Learning 3
Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality 4
Editable Neural Networks 6
Effect of Activation Functions on the Training of Overparametrized Neural Nets 2
Efficient Probabilistic Logic Reasoning with Graph Neural Networks 6
Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform 5
Efficient and Information-Preserving Future Frame Prediction and Beyond 3
Emergence of functional and structural properties of the head direction system by optimization of recurrent neural networks 1
Emergent Tool Use From Multi-Agent Autocurricula 2
Empirical Bayes Transductive Meta-Learning with Synthetic Gradients 5
Empirical Studies on the Properties of Linear Regions in Deep Neural Networks 2
Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation 6
Encoding word order in complex embeddings 6
End to End Trainable Active Contours via Differentiable Rendering 5
Energy-based models for atomic-resolution protein conformations 6
Enhancing Adversarial Defense by k-Winners-Take-All 3
Enhancing Transformation-Based Defenses Against Adversarial Attacks with a Distribution Classifier 3
Ensemble Distribution Distillation 3
Environmental drivers of systematicity and generalization in a situated agent 1
Episodic Reinforcement Learning with Associative Memory 3
Escaping Saddle Points Faster with Stochastic Momentum 2
Estimating Gradients for Discrete Random Variables by Sampling without Replacement 4
Estimating counterfactual treatment outcomes over time through adversarially balanced representations 6
Evaluating The Search Phase of Neural Architecture Search 3
Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning 4
Expected Information Maximization: Using the I-Projection for Mixture Density Estimation 5
Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution 4
Explanation by Progressive Exaggeration 2
Exploration in Reinforcement Learning with Deep Covering Options 3
Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning 3
Exploring Model-based Planning with Policy Networks 4
Extreme Classification via Adversarial Softmax Approximation 4
Extreme Tensoring for Low-Memory Preconditioning 4
FEW-SHOT LEARNING ON GRAPHS VIA SUPER-CLASSES BASED ON GRAPH SPECTRAL MEASURES 4
FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary 4
FSPool: Learning Set Representations with Featurewise Sort Pooling 5
Fair Resource Allocation in Federated Learning 7
Fantastic Generalization Measures and Where to Find Them 3
Fast Neural Network Adaptation via Parameter Remapping and Architecture Search 6
Fast Task Inference with Variational Intrinsic Successor Features 3
Fast is better than free: Revisiting adversarial training 5
FasterSeg: Searching for Faster Real-time Semantic Segmentation 6
Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection 6
Federated Adversarial Domain Adaptation 5
Federated Learning with Matched Averaging 5
Few-shot Text Classification with Distributional Signatures 6
Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents 4
Finite Depth and Width Corrections to the Neural Tangent Kernel 0
Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object Tracking 4
Four Things Everyone Should Know to Improve Batch Normalization 5
FreeLB: Enhanced Adversarial Training for Natural Language Understanding 5
Frequency-based Search-control in Dyna 4
From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech 3
From Variational to Deterministic Autoencoders 4
Functional Regularisation for Continual Learning with Gaussian Processes 4
Functional vs. parametric equivalence of ReLU networks 0
GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification 6
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations 4
GLAD: Learning Sparse Graph Recovery 6
Gap-Aware Mitigation of Gradient Staleness 5
GenDICE: Generalized Offline Estimation of Stationary Values 4
Generalization bounds for deep convolutional neural networks 2
Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint 1
Generalization through Memorization: Nearest Neighbor Language Models 4
Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition 4
Generative Models for Effective ML on Private, Decentralized Datasets 5
Generative Ratio Matching Networks 4
Geom-GCN: Geometric Graph Convolutional Networks 3
Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete Learning 2
Geometric Insights into the Convergence of Nonlinear TD Learning 0
Global Relational Models of Source Code 5
Gradient $\ell_1$ Regularization for Quantization Robustness 3
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks 3
Gradient-Based Neural DAG Learning 4
Gradientless Descent: High-Dimensional Zeroth-Order Optimization 3
Gradients as Features for Deep Representation Learning 3
Graph Constrained Reinforcement Learning for Natural Language Action Spaces 3
Graph Convolutional Reinforcement Learning 3
Graph Neural Networks Exponentially Lose Expressive Power for Node Classification 5
Graph inference learning for semi-supervised classification 3
GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation 5
GraphSAINT: Graph Sampling Based Inductive Learning Method 7
GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding 5
Guiding Program Synthesis by Learning to Generate Examples 3
HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS 4
Hamiltonian Generative Networks 2
Harnessing Structures for Value-Based Planning and Reinforcement Learning 3
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks 3
HiLLoC: lossless image compression with hierarchical latent variable models 5
Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation 4
High Fidelity Speech Synthesis with Adversarial Networks 4
Higher-Order Function Networks for Learning Composable 3D Object Representations 5
How much Position Information Do Convolutional Neural Networks Encode? 2
How to 0wn the NAS in Your Spare Time 5
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs 3
Hypermodels for Exploration 1
I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively 5
IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks 3
Identifying through Flows for Recovering Latent Representations 1
Identity Crisis: Memorization and Generalization Under Extreme Overparameterization 2
Image-guided Neural Object Rendering 3
Imitation Learning via Off-Policy Distribution Matching 4
Implementation Matters in Deep RL: A Case Study on PPO and TRPO 4
Implementing Inductive bias for different navigation tasks through diverse RNN attrractors 1
Implicit Bias of Gradient Descent based Adversarial Training on Separable Data 3
Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin 4
Improved memory in recurrent neural networks with sequential non-normal dynamics 4
Improving Adversarial Robustness Requires Revisiting Misclassified Examples 3
Improving Generalization in Meta Reinforcement Learning using Learned Objectives 5
Improving Neural Language Generation with Spectrum Control 4
In Search for a SAT-friendly Binarized Neural Network Architecture 2
Incorporating BERT into Neural Machine Translation 5
Inductive Matrix Completion Based on Graph Neural Networks 5
Inductive and Unsupervised Representation Learning on Graph Structured Objects 2
Inductive representation learning on temporal graphs 4
Infinite-Horizon Differentiable Model Predictive Control 3
Infinite-horizon Off-Policy Policy Evaluation with Multiple Behavior Policies 2
Influence-Based Multi-Agent Exploration 2
InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization 3
Information Geometry of Orthogonal Initializations and Training 3
Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models 5
Intensity-Free Learning of Temporal Point Processes 4
Interpretable Complex-Valued Neural Networks for Privacy Protection 2
Intriguing Properties of Adversarial Training at Scale 2
Intrinsic Motivation for Encouraging Synergistic Behavior 2
Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems 4
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? 0
Iterative energy-based projection on a normal data manifold for anomaly localization 2
Jacobian Adversarially Regularized Networks for Robustness 4
Jelly Bean World: A Testbed for Never-Ending Learning 4
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps 6
Keep Doing What Worked: Behavior Modelling Priors for Offline Reinforcement Learning 3
Kernel of CycleGAN as a principal homogeneous space 2
Kernelized Wasserstein Natural Gradient 3
Knowledge Consistency between Neural Networks and Beyond 2
LAMOL: LAnguage MOdeling for Lifelong Language Learning 3
LEARNED STEP SIZE QUANTIZATION 4
LEARNING EXECUTION THROUGH NEURAL CODE FUSION 3
Lagrangian Fluid Simulation with Continuous Convolutions 5
LambdaNet: Probabilistic Type Inference using Graph Neural Networks 4
Language GANs Falling Short 3
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes 6
Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings 3
Lazy-CFR: fast and near-optimal regret minimization for extensive games with imperfect information 3
Learn to Explain Efficiently via Neural Logic Inductive Learning 4
Learning Compositional Koopman Operators for Model-Based Control 2
Learning Disentangled Representations for CounterFactual Regression 1
Learning Efficient Parameter Server Synchronization Policies for Distributed SGD 3
Learning Expensive Coordination: An Event-Based Deep RL Approach 3
Learning Heuristics for Quantified Boolean Formulas through Reinforcement Learning 5
Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech 3
Learning Nearly Decomposable Value Functions Via Communication Minimization 3
Learning Robust Representations via Multi-View Information Bottleneck 6
Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling 3
Learning Space Partitions for Nearest Neighbor Search 3
Learning The Difference That Makes A Difference With Counterfactually-Augmented Data 4
Learning To Explore Using Active Neural SLAM 4
Learning deep graph matching with channel-independent embedding and Hungarian attention 2
Learning from Explanations with Neural Execution Tree 4
Learning from Rules Generalizing Labeled Exemplars 5
Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping 5
Learning representations for binary-classification without backpropagation 4
Learning the Arrow of Time for Problems in Reinforcement Learning 4
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks 4
Learning to Control PDEs with Differentiable Physics 4
Learning to Coordinate Manipulation Skills via Skill Behavior Diversification 4
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories 4
Learning to Guide Random Search 5
Learning to Learn by Zeroth-Order Oracle 3
Learning to Link 2
Learning to Move with Affordance Maps 1
Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees 2
Learning to Represent Programs with Property Signatures 3
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering 4
Learning to solve the credit assignment problem 3
Learning transport cost from subset correspondence 4
Learning-Augmented Data Stream Algorithms 3
Linear Symmetric Quantization of Neural Networks for Low-precision Integer Hardware 4
Lipschitz constant estimation of Neural Networks via sparse polynomial optimization 4
Lite Transformer with Long-Short Range Attention 5
Locality and Compositionality in Zero-Shot Learning 3
Logic and the 2-Simplicial Transformer 4
Lookahead: A Far-sighted Alternative of Magnitude-based Pruning 5
Low-Resource Knowledge-Grounded Dialogue Generation 3
Low-dimensional statistical manifold embedding of directed graphs 5
MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius 5
MEMO: A Deep Network for Flexible Combination of Episodic Memories 3
MMA Training: Direct Input Space Margin Maximization through Adversarial Training 5
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems 3
Making Sense of Reinforcement Learning and Probabilistic Inference 3
Masked Based Unsupervised Content Transfer 3
Massively Multilingual Sparse Word Representations 6
Mathematical Reasoning in Latent Space 3
Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning 2
Maxmin Q-learning: Controlling the Estimation Bias of Q-learning 4
Measuring Compositional Generalization: A Comprehensive Method on Realistic Data 4
Measuring and Improving the Use of Graph Information in Graph Neural Networks 3
Measuring the Reliability of Reinforcement Learning Algorithms 3
Memory-Based Graph Networks 4
Meta Dropout: Learning to Perturb Latent Features for Generalization 4
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies 3
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples 4
Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization 3
Meta-Learning Deep Energy-Based Memory Models 4
Meta-Learning with Warped Gradient Descent 5
Meta-Learning without Memorization 5
Meta-Q-Learning 4
Meta-learning curiosity algorithms 4
MetaPix: Few-Shot Video Retargeting 4
Minimizing FLOPs to Learn Efficient Sparse Representations 5
Mirror-Generative Neural Machine Translation 5
Mixed Precision DNNs: All you need is a good parametrization 5
Mixed-curvature Variational Autoencoders 4
Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models 3
Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks 5
Model Based Reinforcement Learning for Atari 5
Model-Augmented Actor-Critic: Backpropagating through Paths 4
Model-based reinforcement learning for biological sequence design 4
Mogrifier LSTM 4
Monotonic Multihead Attention 5
Multi-Agent Interactions Modeling with Correlated Policies 4
Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells 4
Multi-agent Reinforcement Learning for Networked System Control 4
Multilingual Alignment of Contextual Word Representations 3
Multiplicative Interactions and Where to Find Them 3
Mutual Information Gradient Estimation for Representation Learning 4
Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification 5
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting 3
NAS evaluation is frustratingly hard 6
NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search 6
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search 5
Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks 4
Network Deconvolution 4
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning 5
NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension 3
Neural Arithmetic Units 6
Neural Epitome Search for Architecture-Agnostic Network Compression 3
Neural Execution of Graph Algorithms 2
Neural Machine Translation with Universal Visual Representation 7
Neural Module Networks for Reasoning over Text 4
Neural Network Branching for Neural Network Verification 5
Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data 6
Neural Outlier Rejection for Self-Supervised Keypoint Learning 4
Neural Policy Gradient Methods: Global Optimality and Rates of Convergence 1
Neural Stored-program Memory 3
Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension 4
Neural Tangents: Fast and Easy Infinite Neural Networks in Python 3
Neural Text Generation With Unlikelihood Training 3
Neural tangent kernels, transportation mappings, and universal approximation 0
Never Give Up: Learning Directed Exploration Strategies 3
Non-Autoregressive Dialog State Tracking 4
Novelty Detection Via Blurring 3
Oblique Decision Trees from Derivatives of ReLU Networks 4
Observational Overfitting in Reinforcement Learning 2
On Bonus Based Exploration Methods In The Arcade Learning Environment 2
On Computation and Generalization of Generative Adversarial Imitation Learning 1
On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning 4
On Identifiability in Transformers 4
On Mutual Information Maximization for Representation Learning 3
On Robustness of Neural Ordinary Differential Equations 2
On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach 4
On Universal Equivariant Set Networks 5
On the "steerability" of generative adversarial networks 3
On the Convergence of FedAvg on Non-IID Data 2
On the Equivalence between Positional Node Embeddings and Structural Graph Representations 7
On the Global Convergence of Training Deep Linear ResNets 2
On the Need for Topology-Aware Generative Models for Manifold-Based Defenses 1
On the Relationship between Self-Attention and Convolutional Layers 3
On the Variance of the Adaptive Learning Rate and Beyond 5
On the Weaknesses of Reinforcement Learning for Neural Machine Translation 3
On the interaction between supervision and self-play in emergent communication 4
Once-for-All: Train One Network and Specialize it for Efficient Deployment 6
One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation 5
Online and stochastic optimization beyond Lipschitz continuity: A Riemannian approach 1
Optimal Strategies Against Generative Attacks 4
Optimistic Exploration even with a Pessimistic Initialisation 4
Option Discovery using Deep Skill Chaining 5
Order Learning and Its Application to Age Estimation 4
Overlearning Reveals Sensitive Attributes 3
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction 5
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search 5
PCMC-Net: Feature-based Pairwise Choice Markov Chains 4
PROGRESSIVE LEARNING AND DISENTANGLEMENT OF HIERARCHICAL REPRESENTATIONS 3
Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks 5
PairNorm: Tackling Oversmoothing in GNNs 5
Pay Attention to Features, Transfer Learn Faster CNNs 3
Permutation Equivariant Models for Compositional Generalization in Language 4
Phase Transitions for the Information Bottleneck in Representation Learning 3
Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from Video 2
Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics 5
Picking Winning Tickets Before Training by Preserving Gradient Flow 4
Piecewise linear activations substantially shape the loss surfaces of neural networks 0
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning 5
Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP 2
Plug and Play Language Models: A Simple Approach to Controlled Text Generation 4
Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring 6
Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks 0
Population-Guided Parallel Policy Search for Reinforcement Learning 4
Posterior sampling for multi-agent reinforcement learning: solving extensive games with imperfect information 3
Pre-training Tasks for Embedding-based Large-scale Retrieval 4
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations 3
Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks 4
Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control 2
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model 4
Principled Weight Initialization for Hypernetworks 2
Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural Networks 4
Probability Calibration for Knowledge Graph Embedding Models 6
Program Guided Agent 4
Progressive Memory Banks for Incremental Domain Adaptation 5
Projection-Based Constrained Policy Optimization 4
Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks 1
Provable Filter Pruning for Efficient Neural Networks 6
Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$ 3
ProxSGD: Training Structured Neural Networks under Regularization and Constraints 4
Pruned Graph Scattering Transforms 3
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving 5
Pure and Spurious Critical Points: a Geometric Study of Linear Networks 1
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP 1
Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel 6
Quantifying the Cost of Reliable Photo Authentication via High-Performance Learned Lossy Representations 5
Quantum Algorithms for Deep Convolutional Neural Networks 3
Query-efficient Meta Attack to Deep Neural Networks 4
Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings 4
RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis 3
RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments 2
RNA Secondary Structure Prediction By Learning Unrolled Algorithms 6
RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients? 6
RTFM: Generalising to New Environment Dynamics via Reading 2
RaCT: Toward Amortized Ranking-Critical Training For Collaborative Filtering 5
RaPP: Novelty Detection with Reconstruction along Projection Pathway 4
Ranking Policy Gradient 4
Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML 5
ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning 3
ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring 5
Real or Not Real, that is the Question 3
Reanalysis of Variance Reduced Temporal Difference Learning 3
Reconstructing continuous distributions of 3D protein structure from cryo-EM images 4
Recurrent neural circuits for contour detection 5
Reducing Transformer Depth on Demand with Structured Dropout 5
Reformer: The Efficient Transformer 4
Regularizing activations in neural networks via distribution matching with the Wasserstein metric 5
Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs 4
Reinforced active learning for image segmentation 3
Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation 4
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives 3
Relational State-Space Model for Stochastic Multi-Object Systems 4
Residual Energy-Based Models for Text Generation 5
Restricting the Flow: Information Bottlenecks for Attribution 5
Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness 5
Rethinking the Hyperparameters for Fine-tuning 4
Revisiting Self-Training for Neural Sequence Generation 5
Ridge Regression: Structure, Cross-Validation, and Sketching 4
Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural Networks 2
Robust Local Features for Improving the Generalization of Adversarial Training 4
Robust Reinforcement Learning for Continuous Control with Model Misspecification 4
Robust Subspace Recovery Layer for Unsupervised Anomaly Detection 5
Robust anomaly detection and backdoor attack detection via differential privacy 4
Robust training with ensemble consensus 3
Robustness Verification for Transformers 4
Rotation-invariant clustering of neuronal responses in primary visual cortex 2
Rényi Fair Inference 4
SAdam: A Variant of Adam for Strongly Convex Functions 3
SCALOR: Generative World Models with Scalable Object Representations 3
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference 5
SELF: Learning to Filter Noisy Labels with Self-Ensembling 4
SNODE: Spectral Discretization of Neural ODEs for System Identification 3
SNOW: Subscribing to Knowledge via Channel Pooling for Transfer & Lifelong Learning of Convolutional Neural Networks 5
SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition 5
SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards 3
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models 4
SVQN: Sequential Variational Soft Q-Learning Networks 2
Sample Efficient Policy Gradient Methods with Recursive Variance Reduction 3
Sampling-Free Learning of Bayesian Quantized Neural Networks 2
Scalable Model Compression by Entropy Penalized Reparameterization 3
Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base 5
Scalable and Order-robust Continual Learning with Additive Parameter Decomposition 4
Scale-Equivariant Steerable Networks 5
Scaling Autoregressive Video Models 4
Selection via Proxy: Efficient Data Selection for Deep Learning 6
Self-Adversarial Learning with Comparative Discrimination for Text Generation 3
Self-Supervised Learning of Appliance Usage 4
Self-labelling via simultaneous clustering and representation learning 4
Semantically-Guided Representation Learning for Self-Supervised Monocular Depth 4
Semi-Supervised Generative Modeling for Controllable Speech Synthesis 4
Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue 4
Sharing Knowledge in Multi-Task Deep Reinforcement Learning 4
Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks 3
Short and Sparse Deconvolution --- A Geometric Approach 4
Sign Bits Are All You Need for Black-Box Attacks 6
Sign-OPT: A Query-Efficient Hard-label Adversarial Attack 4
Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee 2
Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning 4
Single Episode Policy Transfer in Reinforcement Learning 5
Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets 3
Sliced Cramer Synaptic Consolidation for Preserving Deeply Learned Representations 3
SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum 5
Smooth markets: A basic mechanism for organizing gradient-based learners 0
Smoothness and Stability in GANs 2
Span Recovery for Deep Neural Networks with Applications to Input Obfuscation 3
Sparse Coding with Gated Learned ISTA 4
Spectral Embedding of Regularized Block Models 3
Spike-based causal inference for weight alignment 2
SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with Spikes 5
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs 4
State Alignment-based Imitation Learning 3
State-only Imitation with Transition Dynamics Mismatch 4
Stochastic AUC Maximization with Deep Neural Networks 4
Stochastic Conditional Generative Networks with Basis Decomposition 3
Stochastic Weight Averaging in Parallel: Large-Batch Training That Generalizes Well 4
Strategies for Pre-training Graph Neural Networks 5
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding 4
StructPool: Structured Graph Pooling via Conditional Random Fields 5
Structured Object-Aware Physics Prediction for Video Modeling and Planning 3
Sub-policy Adaptation for Hierarchical Reinforcement Learning 3
Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control 3
Symplectic Recurrent Neural Networks 2
Synthesizing Programmatic Policies that Inductively Generalize 2
TabFact: A Large-scale Dataset for Table-based Fact Verification 6
Target-Embedding Autoencoders for Supervised Representation Learning 4
Tensor Decompositions for Temporal Knowledge Base Completion 5
The Break-Even Point on Optimization Trajectories of Deep Neural Networks 3
The Curious Case of Neural Text Degeneration 3
The Early Phase of Neural Network Training 2
The Gambler's Problem and Beyond 0
The Implicit Bias of Depth: How Incremental Learning Drives Generalization 2
The Ingredients of Real World Robotic Reinforcement Learning 2
The Local Elasticity of Neural Networks 3
The Logical Expressiveness of Graph Neural Networks 4
The Shape of Data: Intrinsic Distance for Data Distributions 5
The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget 3
The asymptotic spectrum of the Hessian of DNN throughout training 2
The intriguing role of module criticality in the generalization of deep networks 2
Theory and Evaluation Metrics for Learning Disentangled Representations 3
Thieves on Sesame Street! Model Extraction of BERT-based APIs 2
Thinking While Moving: Deep Reinforcement Learning with Concurrent Control 4
To Relieve Your Headache of Training an MRF, Take AdVIL 5
Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control 3
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets 4
Towards Fast Adaptation of Neural Architectures with Meta Learning 6
Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models 2
Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization 4
Towards Stable and Efficient Training of Verifiably Robust Neural Networks 4
Towards Verified Robustness under Text Deletion Interventions 3
Towards a Deep Network Architecture for Structured Smoothness 5
Towards neural networks that provably know when they don't know 4
Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators 4
Training Recurrent Neural Networks Online by Learning Explicit State Variables 3
Training binary neural networks with real-to-binary convolutions 4
Training individually fair ML models with sensitive subspace robustness 5
Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds 1
Transferable Perturbations of Deep Feature Distributions 3
Transferring Optimality Across Data Distributions via Homotopy Methods 3
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention 4
Tree-Structured Attention with Hierarchical Accumulation 5
Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference 4
Truth or backpropaganda? An empirical investigation of deep learning theory 2
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation 3
Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent Variable Models 5
Uncertainty-guided Continual Learning with Bayesian Neural Networks 5
Understanding Architectures Learnt by Cell-based Neural Architecture Search 3
Understanding Generalization in Recurrent Neural Networks 0
Understanding Knowledge Distillation in Non-autoregressive Machine Translation 4
Understanding Why Neural Networks Generalize Well Through GSNR of Parameters 2
Understanding and Improving Information Transfer in Multi-Task Learning 5
Understanding and Robustifying Differentiable Architecture Search 5
Understanding l4-based Dictionary Learning: Interpretation, Stability, and Robustness 3
Understanding the Limitations of Conditional Generative Models 2
Understanding the Limitations of Variational Mutual Information Estimators 2
Universal Approximation with Certified Networks 0
Unpaired Point Cloud Completion on Real Scans using Adversarial Training 2
Unrestricted Adversarial Examples via Semantic Manipulation 2
Unsupervised Clustering using Pseudo-semi-supervised Learning 4
Unsupervised Model Selection for Variational Disentangled Representation Learning 3
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control 4
V4D: 4D Convolutional Neural Networks for Video-level Representation Learning 4
VL-BERT: Pre-training of Generic Visual-Linguistic Representations 5
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning 4
Variance Reduction With Sparse Gradients 3
Variational Autoencoders for Highly Multivariate Spatial Point Processes Intensities 5
Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling 6
Variational Recurrent Models for Solving Partially Observable Control Tasks 5
Variational Template Machine for Data-to-Text Generation 5
Vid2Game: Controllable Characters Extracted from Real-World Videos 2
VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation 4
Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search 5
Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards 5
Weakly Supervised Clustering by Exploiting Unique Class Count 4
Weakly Supervised Disentanglement with Guarantees 3
What Can Neural Networks Reason About? 3
What graph neural networks cannot learn: depth vs width 2
White Noise Analysis of Neural Networks 4
Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity 4
Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks 5
You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings 4
You Only Train Once: Loss-Conditional Training of Deep Networks 4
Your classifier is secretly an energy based model and you should treat it like one 3
vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations 4
word2ket: Space-efficient Word Embeddings inspired by Quantum Entanglement 5