DPSNet: End-to-end Deep Plane Sweep Stereo by Sunghoon Im et al.
Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution by Thomas Elsken et al.
Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs by Sachin Kumar et al.
Music Transformer: Generating Music with Long-Term Structure by Cheng-Zhi Anna Huang et al.
Deterministic Variational Inference for Robust Bayesian Neural Networks by Anqi Wu et al.
Learning to Remember More with Less Memorization by Hung Le et al.
KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks by James Jordon et al.
Smoothing the Geometry of Probabilistic Box Embeddings by Xiang Li et al.
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset by Curtis Hawthorne et al.
A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs by Jack Lindsey et al.
BA-Net: Dense Bundle Adjustment Networks by Chengzhou Tang et al.
Meta-Learning Update Rules for Unsupervised Representation Learning by Luke Metz et al.
GENERATING HIGH FIDELITY IMAGES WITH SUBSCALE PIXEL NETWORKS AND MULTIDIMENSIONAL UPSCALING by Jacob Menick et al.
Understanding Composition of Word Embeddings via Tensor Decomposition by Abraham Frandsen et al.
Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology by Bastian Rieck et al.
Spherical CNNs on Unstructured Grids by Chiyu Max Jiang et al.
Information asymmetry in KL-regularized RL by Alexandre Galashov et al.
Integer Networks for Data Compression with Latent-Variable Models by Johannes Ballé et al.
Deep learning generalizes because the parameter-function map is biased towards simple functions by Guillermo Valle-Perez et al.
Hindsight policy gradients by Paulo Rauber et al.
Critical Learning Periods in Deep Networks by Alessandro Achille et al.
Dynamic Channel Pruning: Feature Boosting and Suppression by Xitong Gao et al.
Learning to Navigate the Web by Izzeddin Gur et al.
Hierarchical Generative Modeling for Controllable Speech Synthesis by Wei-Ning Hsu et al.
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding by Alex Wang et al.
Variational Autoencoder with Arbitrary Conditioning by Oleg Ivanov et al.
Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic by Mikael Henaff et al.
Learning to Design RNA by Frederic Runge et al.
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks by Joshua J. Michalenko et al.
Toward Understanding the Impact of Staleness in Distributed Machine Learning by Wei Dai et al.
M^3RL: Mind-aware Multi-agent Management Reinforcement Learning by Tianmin Shu et al.
Transfer Learning for Sequences via Learning to Collocate by Wanyun Cui et al.
DHER: Hindsight Experience Replay for Dynamic Goals by Meng Fang et al.
Learning Programmatically Structured Representations with Perceptor Gradients by Svetlin Penkov et al.
Function Space Particle Optimization for Bayesian Neural Networks by Ziyu Wang et al.
Fixup Initialization: Residual Learning Without Normalization by Hongyi Zhang et al.
Execution-Guided Neural Program Synthesis by Xinyun Chen et al.
GANSynth: Adversarial Neural Audio Synthesis by Jesse Engel et al.
Generating Multi-Agent Trajectories using Programmatic Weak Supervision by Eric Zhan et al.
Discovery of Natural Language Concepts in Individual Units of CNNs by Seil Na et al.
Unsupervised Domain Adaptation for Distance Metric Learning by Kihyuk Sohn et al.
Graph Wavelet Neural Network by Bingbing Xu et al.
SNIP: Single-Shot Network Pruning Based on Connection Sensitivity by Namhoon Lee et al.
Structured Neural Summarization by Patrick Fernandes et al.
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model by Florian Mai et al.
Identifying and Controlling Important Neurons in Neural Machine Translation by Anthony Bau et al.
Environment Probing Interaction Policies by Wenxuan Zhou et al.
TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer by Sicong Huang et al.
Efficient Training on Very Large Corpora via Gramian Estimation by Walid Krichene et al.
DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder by Xiaodong Gu et al.
LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos by Elke Kirschbaum et al.
Adversarial Imitation via Variational Inverse Reinforcement Learning by Ahmed H. Qureshi et al.
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks by Jose Oramas et al.
Measuring Compositionality in Representation Learning by Jacob Andreas
Residual Non-local Attention Networks for Image Restoration by Yulun Zhang et al.
Overcoming the Disentanglement vs Reconstruction Trade-off via Jacobian Supervision by José Lezama
Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation by Sang-Woo Lee et al.
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees by Yuping Luo et al.
Generating Liquid Simulations with Deformation-aware Neural Networks by Lukas Prantl et al.
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space by Zhiqing Sun et al.
Random mesh projectors for inverse problems by Konik Kothari* et al.
Trellis Networks for Sequence Modeling by Shaojie Bai et al.
A Variational Inequality Perspective on Generative Adversarial Networks by Gauthier Gidel et al.
DELTA: DEEP LEARNING TRANSFER USING FEATURE MAP WITH ATTENTION FOR CONVOLUTIONAL NETWORKS by Xingjian Li et al.
What do you learn from context? Probing for sentence structure in contextualized word representations by Ian Tenney et al.
On Self Modulation for Generative Adversarial Networks by Ting Chen et al.
Meta-Learning For Stochastic Gradient MCMC by Wenbo Gong et al.
Learning what and where to attend by Drew Linsley et al.
Adversarial Domain Adaptation for Stable Brain-Machine Interfaces by Ali Farshchian et al.
Do Deep Generative Models Know What They Don't Know? by Eric Nalisnick et al.
Discriminator Rejection Sampling by Samaneh Azadi et al.
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware by Han Cai et al.
Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning by Anusha Nagabandi et al.
Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL by Anusha Nagabandi et al.
Quasi-hyperbolic momentum and Adam for deep learning by Jerry Ma et al.
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience by Vaishnavh Nagarajan et al.
Learning Finite State Representations of Recurrent Policy Networks by Anurag Koul et al.
Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization by Navid Azizan et al.
CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild by Yang Zhang et al.
Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability Detection by Tue Le et al.
Diversity is All You Need: Learning Skills without a Reward Function by Benjamin Eysenbach et al.
On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization by Xiangyi Chen et al.
Learning to Schedule Communication in Multi-agent Reinforcement Learning by Daewoo Kim et al.
Combinatorial Attacks on Binarized Neural Networks by Elias B Khalil et al.
Feature-Wise Bias Amplification by Klas Leino et al.
Two-Timescale Networks for Nonlinear Value Function Approximation by Wesley Chung et al.
Deep Frank-Wolfe For Neural Network Optimization by Leonard Berrada et al.
Meta-learning with differentiable closed-form solvers by Luca Bertinetto et al.
Neural Program Repair by Jointly Learning to Localize and Repair by Marko Vasic et al.
MisGAN: Learning from Incomplete Data with Generative Adversarial Networks by Steven Cheng-Xian Li et al.
Stable Opponent Shaping in Differentiable Games by Alistair Letcher et al.
Poincare Glove: Hyperbolic Word Embeddings by Alexandru Tifrea* et al.
Spectral Inference Networks: Unifying Deep and Spectral Learning by David Pfau et al.
Dimensionality Reduction for Representing the Knowledge of Probabilistic Models by Marc T Law et al.
Learning protein sequence embeddings using information from structure by Tristan Bepler et al.
Learning what you can do before doing anything by Oleh Rybkin et al.
Efficient Augmentation via Data Subsampling by Michael Kuchnik et al.
Adversarial Reprogramming of Neural Networks by Gamaleldin F. Elsayed et al.
Don't let your Discriminator be fooled by Brady Zhou et al.
A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation by Akhilesh Gotmare et al.
Feature Intertwiner for Object Detection by Hongyang Li et al.
Unsupervised Learning via Meta-Learning by Kyle Hsu et al.
Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer by Ori Press et al.
Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking by Haichuan Yang et al.
Reward Constrained Policy Optimization by Chen Tessler et al.
Optimal Completion Distillation for Sequence Learning by Sara Sabour et al.
Large-Scale Study of Curiosity-Driven Learning by Yuri Burda et al.
RelGAN: Relational Generative Adversarial Networks for Text Generation by Weili Nie et al.
The Singular Values of Convolutional Layers by Hanie Sedghi et al.
Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere Convolution by Min Liu et al.
On the loss landscape of a class of deep neural networks with no bad local valleys by Quynh Nguyen et al.
Towards Metamerism via Foveated Style Transfer by Arturo Deza et al.
Kernel RNN Learning (KeRNL) by Christopher Roth et al.
Large Scale Graph Learning From Smooth Signals by Vassilis Kalofolias et al.
Riemannian Adaptive Optimization Methods by Gary Becigneul et al.
Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers by Alexander Shekhovtsov et al.
Competitive experience replay by Hao Liu et al.
Synthetic Datasets for Neural Program Synthesis by Richard Shin et al.
FUNCTIONAL VARIATIONAL BAYESIAN NEURAL NETWORKS by Shengyang Sun et al.
Analysis of Quantized Models by Lu Hou et al.
Composing Complex Skills by Learning Transition Policies by Youngwoon Lee* et al.
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders by Junxian He et al.
AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks by Bo Chang et al.
Variance Networks: When Expectation Does Not Meet Your Expectations by Kirill Neklyudov et al.
Universal Transformers by Mostafa Dehghani et al.
InfoBot: Transfer and Exploration via the Information Bottleneck by Anirudh Goyal et al.
Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation by Ehsan Hosseini-Asl et al.
Recall Traces: Backtracking Models for Efficient Reinforcement Learning by Anirudh Goyal et al.
Explaining Image Classifiers by Counterfactual Generation by Chun-Hao Chang et al.
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes by Roman Novak et al.
Automatically Composing Representation Transformations as a Means for Generalization by Michael Chang et al.
Guiding Policies with Language via Meta-Learning by John D. Co-Reyes et al.
MARGINALIZED AVERAGE ATTENTIONAL NETWORK FOR WEAKLY-SUPERVISED LEARNING by Yuan Yuan et al.
InstaGAN: Instance-aware Image-to-Image Translation by Sangwoo Mo et al.
Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability by Kai Y. Xiao et al.
Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs by Ryan L. Murphy et al.
RNNs implicitly implement tensor-product representations by R. Thomas McCoy et al.
Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors by Andrew Ilyas et al.
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length by Stanisław Jastrzębski et al.
LanczosNet: Multi-Scale Deep Graph Convolutional Networks by Renjie Liao et al.
Human-level Protein Localization with Convolutional Neural Networks by Elisabeth Rumetshofer et al.
Adaptive Gradient Methods with Dynamic Bound of Learning Rate by Liangchen Luo et al.
Eidetic 3D LSTM: A Model for Video Prediction and Beyond by Yunbo Wang et al.
Neural Graph Evolution: Towards Efficient Automatic Robot Design by Tingwu Wang et al.
Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks by Charbel Sakr et al.
The Deep Weight Prior by Andrei Atanov et al.
Evaluating Robustness of Neural Networks with Mixed Integer Programming by Vincent Tjeng et al.
Quaternion Recurrent Neural Networks by Titouan Parcollet et al.
On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data by Nan Lu et al.
Diffusion Scattering Transforms on Graphs by Fernando Gama et al.
Optimal Control Via Neural Networks: A Convex Approach by Yize Chen et al.
Multiple-Attribute Text Rewriting by Guillaume Lample et al.
Wasserstein Barycenter Model Ensembling by Pierre Dognin* et al.
code2seq: Generating Sequences from Structured Representations of Code by Uri Alon et al.
Slimmable Neural Networks by Jiahui Yu et al.
Learning Two-layer Neural Networks with Symmetric Inputs by Rong Ge et al.
Latent Convolutional Models by ShahRukh Athar et al.
DOM-Q-NET: Grounded RL on Structured Language by Sheng Jia et al.
Cost-Sensitive Robustness against Adversarial Examples by Xiao Zhang et al.
h-detach: Modifying the LSTM Gradient Towards Better Optimization by Bhargav Kanuparthi et al.
Systematic Generalization: What Is Required and Can It Be Learned? by Dzmitry Bahdanau* et al.
Efficient Lifelong Learning with A-GEM by Arslan Chaudhry et al.
Harmonic Unpaired Image-to-image Translation by Rui Zhang et al.
AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active Tracking by Fangwei Zhong et al.
Improving MMD-GAN Training with Repulsive Loss Function by Wei Wang et al.
On the Turing Completeness of Modern Neural Network Architectures by Jorge Pérez et al.
Complement Objective Training by Hao-Yun Chen et al.
Variance Reduction for Reinforcement Learning in Input-Driven Environments by Hongzi Mao et al.
Learning Self-Imitating Diverse Policies by Tanmay Gangwani et al.
Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams by Mohammad Kachuee et al.
Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer by David Berthelot* et al.
Learnable Embedding Space for Efficient Neural Architecture Compression by Shengcao Cao et al.
Variational Autoencoders with Jointly Optimized Latent Dependency Structure by Jiawei He et al.
Learning to Infer and Execute 3D Shape Programs by Yonglong Tian et al.
Episodic Curiosity through Reachability by Nikolay Savinov et al.
Kernel Change-point Detection with Auxiliary Deep Generative Models by Wei-Cheng Chang et al.
Are adversarial examples inevitable? by Ali Shafahi et al.
Beyond Greedy Ranking: Slate Optimization via List-CVAE by Ray Jiang et al.
Stochastic Prediction of Multi-Agent Interactions from Partial Observations by Chen Sun et al.
Preferences Implicit in the State of the World by Rohin Shah et al.
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm by Charbel Sakr et al.
SPIGAN: Privileged Adversarial Learning from Simulation by Kuan-Hui Lee et al.
ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees by Hao He et al.
Practical lossless compression with latent variables using bits back coding by James Townsend et al.
Gradient descent aligns the layers of deep linear networks by Ziwei Ji et al.
Revealing interpretable object representations from human behavior by Charles Y. Zheng et al.
Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency by Liqian Ma et al.
Contingency-Aware Exploration in Reinforcement Learning by Jongwook Choi et al.
Whitening and Coloring Batch Transform for GANs by Aliaksandr Siarohin et al.
Variational Bayesian Phylogenetic Inference by Cheng Zhang et al.
Multi-class classification without multi-class labels by Yen-Chang Hsu et al.
Hierarchical interpretations for neural network predictions by Chandan Singh et al.
Measuring and regularizing networks in function space by Ari Benjamin et al.
Biologically-Plausible Learning Algorithms Can Scale to Large Datasets by Will Xiao et al.
Learning a Meta-Solver for Syntax-Guided Program Synthesis by Xujie Si et al.
Robustness May Be at Odds with Accuracy by Dimitris Tsipras et al.
Time-Agnostic Prediction: Predicting Predictable Video Frames by Dinesh Jayaraman et al.
Interpolation-Prediction Networks for Irregularly Sampled Time Series by Satya Narayan Shukla et al.
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning by Maxime Chevalier-Boisvert et al.
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids by Yunzhu Li et al.
Imposing Category Trees Onto Word-Embeddings Using A Geometric Construction by Tiansi Dong et al.
Diversity-Sensitive Conditional Generative Adversarial Networks by Dingdong Yang et al.
A Kernel Random Matrix-Based Approach for Sparse PCA by Mohamed El Amine Seddik et al.
Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning by Ying Wen et al.
Deep Graph Infomax by Petar Veličković et al.
Adversarial Audio Synthesis by Chris Donahue et al.
Improving Generalization and Stability of Generative Adversarial Networks by Hoang Thanh-Tung et al.
NOODL: Provable Online Dictionary Learning and Sparse Coding by Sirisha Rambhatla et al.
Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds by Cenk Baykal et al.
AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods by Zhiming Zhou* et al.
A Closer Look at Few-shot Classification by Wei-Yu Chen et al.
A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks by Sanjeev Arora et al.
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average by Ben Athiwaratkun et al.
An analytic theory of generalization dynamics and transfer learning in deep linear networks by Andrew K. Lampinen et al.
Learning Multimodal Graph-to-Graph Translation for Molecule Optimization by Wengong Jin et al.
Regularized Learning for Domain Adaptation under Label Shifts by Kamyar Azizzadenesheli et al.
An Empirical Study of Example Forgetting during Deep Neural Network Learning by Mariya Toneva* et al.
INVASE: Instance-wise Variable Selection using Neural Networks by Jinsung Yoon et al.
PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees by James Jordon et al.
Multi-Agent Dual Learning by Yiren Wang et al.
Overcoming Catastrophic Forgetting for Continual Learning via Model Adaptation by Wenpeng Hu et al.
Capsule Graph Neural Network by Zhang Xinyi et al.
Learning Exploration Policies for Navigation by Tao Chen et al.
Deep Layers as Stochastic Solvers by Adel Bibi et al.
Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality by Taiji Suzuki
On the Sensitivity of Adversarial Robustness to Input Data Distributions by Gavin Weiguang Ding et al.
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets by Penghang Yin et al.
Policy Transfer with Strategy Optimization by Wenhao Yu et al.
Learning-Based Frequency Estimation Algorithms by Chen-Yu Hsu et al.
Visual Semantic Navigation using Scene Priors by Wei Yang et al.
LEARNING FACTORIZED REPRESENTATIONS FOR OPEN-SET DOMAIN ADAPTATION by Mahsa Baktashmotlagh et al.
Adversarial Attacks on Graph Neural Networks via Meta Learning by Daniel Zügner et al.
Learning To Simulate by Nataniel Ruiz et al.
A rotation-equivariant convolutional neural network model of primary visual cortex by Alexander S. Ecker et al.
Equi-normalization of Neural Networks by Pierre Stock et al.
GamePad: A Learning Environment for Theorem Proving by Daniel Huang et al.
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation by Chih-Yao Ma et al.
A comprehensive, application-oriented study of catastrophic forgetting in DNNs by B. Pfülb et al.
SOM-VAE: Interpretable Discrete Representation Learning on Time Series by Vincent Fortuin et al.
Towards the first adversarially robust neural network model on MNIST by Lukas Schott et al.
Invariant and Equivariant Graph Networks by Haggai Maron et al.
Deep Convolutional Networks as shallow Gaussian Processes by Adrià Garriga-Alonso et al.
Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors by Vitalii Zhelezniak et al.
Deep reinforcement learning with relational inductive biases by Vinicius Zambaldi et al.
STCN: Stochastic Temporal Convolutional Networks by Emre Aksan et al.
Optimal Transport Maps For Distribution Preserving Operations on Latent Spaces of Generative Models by Eirikur Agustsson et al.
Predict then Propagate: Graph Neural Networks meet Personalized PageRank by Johannes Klicpera et al.
DeepOBS: A Deep Learning Optimizer Benchmark Suite by Frank Schneider et al.
Neural Speed Reading with Structural-Jump-LSTM by Christian Hansen et al.
Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer by Hsueh-Ti Derek Liu et al.
Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications by Carson Eisenach et al.
Analyzing Inverse Problems with Invertible Neural Networks by Lynton Ardizzone et al.
Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity by Thomas Miconi et al.
Sample Efficient Adaptive Text-to-Speech by Yutian Chen et al.
Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives by George Tucker et al.
The relativistic discriminator: a key element missing from standard GAN by Alexia Jolicoeur-Martineau