ICLR 2021

859 papers

Reset-Free Lifelong Learning with Skill-Space Planning

Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch

FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders

Pengyu Cheng, Weituo Hao, Siyang Yuan, Shijing Si, Lawrence Carin

Online Adversarial Purification based on Self-supervised Learning

Changhao Shi, Chester Holtz, Gal Mishne

Adaptive and Generative Zero-Shot Learning

Yu-Ying Chou, Hsuan-tien Lin, Tyng-luh Liu

Contextual Transformation Networks for Online Continual Learning

Quang Pham, Chenghao Liu, Doyen Sahoo, Steven Hoi

A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks

Renjie Liao, Raquel Urtasun, Richard Zemel

Auction Learning as a Two-Player Game

Jad Rahme, Samy Jelassi, S. Matthew Weinberg

Fast And Slow Learning Of Recurrent Independent Mechanisms

Kanika Madan, Nan Rosemary Ke, Anirudh Goyal, Bernhard Schölkopf, Yoshua Bengio

AUXILIARY TASK UPDATE DECOMPOSITION: THE GOOD, THE BAD AND THE NEUTRAL

Lucio M. Dery, Yann Dauphin, David Grangier

Dataset Meta-Learning from Kernel Ridge-Regression

Timothy Nguyen, Zhourong Chen, Jaehoon Lee

Semantic Re-tuning with Contrastive Tension

Fredrik Carlsson, Amaru Cuba Gyllensten, Evangelia Gogoulou, Erik Ylipää Hellqvist, Magnus Sahlgren

HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients

Enmao Diao, Jie Ding, Vahid Tarokh

Probabilistic Numeric Convolutional Neural Networks

Marc Anton Finzi, Roberto Bondesan, Max Welling

Blending MPC & Value Function Approximation for Efficient Reinforcement Learning

Mohak Bhardwaj, Sanjiban Choudhury, Byron Boots

How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?

Zixiang Chen, Yuan Cao, Difan Zou, Quanquan Gu

Revisiting Locally Supervised Learning: an Alternative to End-to-end Training

Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang

Explaining the Efficacy of Counterfactually Augmented Data

Divyansh Kaushik, Amrith Setlur, Eduard H Hovy, Zachary Chase Lipton

Multi-timescale Representation Learning in LSTM Language Models

Shivangi Mahto, Vy Ai Vo, Javier S. Turek, Alexander Huth

Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang

Nonseparable Symplectic Neural Networks

Shiying Xiong, Yunjin Tong, Xingzhe He, Shuqi Yang, Cheng Yang

WaNet - Imperceptible Warping-based Backdoor Attack

Tuan Anh Nguyen, Anh Tuan Tran

DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues

Rishabh Joshi, Vidhisha Balachandran, Shikhar Vashishth, Alan Black, Yulia Tsvetkov

Conditional Generative Modeling via Learning the Latent Space

Sameera Ramasinghe, Kanchana Nisal Ranasinghe, Salman Khan, Nick Barnes, Stephen Gould

Solving Compositional Reinforcement Learning Problems via Task Reduction

Yunfei Li, Yilin Wu, Huazhe Xu, Xiaolong Wang, Yi Wu

On Graph Neural Networks versus Graph-Augmented MLPs

Lei Chen, Zhengdao Chen, Joan Bruna

Linear Last-iterate Convergence in Constrained Saddle-point Optimization

Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, Haipeng Luo

Adaptive Procedural Task Generation for Hard-Exploration Problems

Kuan Fang, Yuke Zhu, Silvio Savarese, L. Fei-Fei

Evaluation of Similarity-based Explanations

Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui

The Recurrent Neural Tangent Kernel

Sina Alemohammad, Zichao Wang, Randall Balestriero, Richard Baraniuk

Learning to Make Decisions via Submodular Regularization

Ayya Alieva, Aiden Aceves, Jialin Song, Stephen Mayo, Yisong Yue

Private Image Reconstruction from System Side Channels Using Generative Models

Yuanyuan Yuan, Shuai Wang, Junping Zhang

Training GANs with Stronger Augmentations via Contrastive Discriminator

Jongheon Jeong, Jinwoo Shin

Learning Better Structured Representations Using Low-rank Adaptive Label Smoothing

Asish Ghoshal, Xilun Chen, Sonal Gupta, Luke Zettlemoyer, Yashar Mehdad

Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms

Arda Sahiner, Tolga Ergen, John M. Pauly, Mert Pilanci

Convex Regularization behind Neural Reconstruction

Arda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John M. Pauly

A Temporal Kernel Approach for Deep Learning with Continuous-time Information

Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

Sample-Efficient Automated Deep Reinforcement Learning

Jörg K.H. Franke, Gregor Koehler, André Biedenkapp, Frank Hutter

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness

Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma

FedMix: Approximation of Mixup under Mean Augmented Federated Learning

Tehrim Yoon, Sumin Shin, Sung Ju Hwang, Eunho Yang

Selective Classification Can Magnify Disparities Across Groups

Erik Jones, Shiori Sagawa, Pang Wei Koh, Ananya Kumar, Percy Liang

RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs

Meng Qu, Junkun Chen, Louis-Pascal Xhonneux, Yoshua Bengio, Jian Tang

Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization

Alexander Korotin, Lingxiao Li, Justin Solomon, Evgeny Burnaev

Group Equivariant Stand-Alone Self-Attention For Vision

David W. Romero, Jean-Baptiste Cordonnier

Wasserstein-2 Generative Networks

Alexander Korotin, Vage Egiazarian, Arip Asadulaev, Alexander Safin, Evgeny Burnaev

SkipW: Resource Adaptable RNN with Strict Upper Computational Limit

Tsiry Mayet, Anne Lambert, Pascal Leguyadec, Francoise Le Bolzer, Francois Schnitzler

Activation-level uncertainty in deep neural networks

Pablo Morales-Alvarez, Daniel Hernández-lobato, Rafael Molina, José Miguel Hernández-Lobato

Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear Time

Yu Cheng, Honghao Lin

A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima

Zeke Xie, Issei Sato, Masashi Sugiyama

You Only Need Adversarial Supervision for Semantic Image Synthesis

Edgar Schonfeld, Vadim Sushko, Dan Zhang, Juergen Gall, Bernt Schiele

Latent Convergent Cross Mapping

Edward De Brouwer, Adam Arany, Jaak Simm, Yves Moreau

LiftPool: Bidirectional ConvNet Pooling

Jiaojiao Zhao, Cees G. M. Snoek

Disentangling 3D Prototypical Networks for Few-Shot Concept Learning

Mihir Prabhudesai, Shamit Lal, Darshan Patil, Hsiao-Yu Tung, Adam W Harley

Physics-aware, probabilistic model order reduction with guaranteed stability

Sebastian Kaltenbach, Phaedon Stelios Koutsourelakis

Rethinking Embedding Coupling in Pre-trained Language Models

Hyung Won Chung, Thibault Fevry, Henry Tsai, Melvin Johnson, Sebastian Ruder

Computational Separation Between Convolutional and Fully-Connected Networks

Eran Malach, Shai Shalev-shwartz

Linear Mode Connectivity in Multitask and Continual Learning

Seyed Iman Mirzadeh, Mehrdad Farajtabar, Dilan Gorur, Razvan Pascanu, Hassan Ghasemzadeh

Capturing Label Characteristics in VAEs

Tom Joy, Sebastian Schmon, Philip Torr, Siddharth N, Tom Rainforth

Learning Energy-Based Models by Diffusion Recovery Likelihood

Ruiqi Gao, Yang Song, Ben Poole, Ying Nian Wu, Diederik P Kingma

Monte-Carlo Planning and Learning with Language Action Value Estimates

Youngsoo Jang, Seokin Seo, Jongmin Lee, Kee-eung Kim

The inductive bias of ReLU networks on orthogonally separable data

Mary Phuong, Christoph H Lampert

Simple Augmentation Goes a Long Way: ADRL for DNN Quantization

Lin Ning, Guoyang Chen, Weifeng Zhang, Xipeng Shen

LEAF: A Learnable Frontend for Audio Classification

Neil Zeghidour, Olivier Teboul, Félix de Chaumont Quitry, Marco Tagliasacchi

End-to-End Egospheric Spatial Memory

Daniel James Lenton, Stephen James, Ronald Clark, Andrew Davison

On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines

Marius Mosbach, Maksym Andriushchenko, Dietrich Klakow

Spatially Structured Recurrent Modules

Nasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal, Manuel Wuthrich, Stefan Bauer

Genetic Soft Updates for Policy Evolution in Deep Reinforcement Learning

Enrico Marchesini, Davide Corsi, Alessandro Farinelli

Boost then Convolve: Gradient Boosting Meets Graph Neural Networks

Sergei Ivanov, Liudmila Prokhorenkova

A statistical theory of cold posteriors in deep neural networks

Laurence Aitchison

Lipschitz Recurrent Neural Networks

N. Benjamin Erichson, Omri Azencot, Alejandro Queiruga, Liam Hodgkinson, Michael W. Mahoney

Hyperbolic Neural Networks++

Ryohei Shimizu, Yusuke Mukuta, Tatsuya Harada

Prototypical Contrastive Learning of Unsupervised Representations

Junnan Li, Pan Zhou, Caiming Xiong, Steven Hoi

Characterizing signal propagation to close the performance gap in unnormalized ResNets

Andrew Brock, Soham De, Samuel L Smith

Private Post-GAN Boosting

Marcel Neunhoeffer, Steven Wu, Cynthia Dwork

Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning

Zhiyuan Li, Yuping Luo, Kaifeng Lyu

HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks

Zhou Xian, Shamit Lal, Hsiao-Yu Tung, Emmanouil Antonios Platanios, Katerina Fragkiadaki

Variational Intrinsic Control Revisited

Taehwan Kwon

Sliced Kernelized Stein Discrepancy

Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing

Tao Yu, Chien-Sheng Wu, Xi Victoria Lin, bailin wang, Yi Chern Tan

Differentiable Segmentation of Sequences

Erik Scharwächter, Jonathan Lennartz, Emmanuel Müller

Improving VAEs' Robustness to Adversarial Attack

Matthew JF Willetts, Alexander Camuto, Tom Rainforth, S Roberts, Christopher C Holmes

Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks

Ingmar Schubert, Ozgur S Oguz, Marc Toussaint

Clairvoyance: A Pipeline Toolkit for Medical Time Series

Daniel Jarrett, Jinsung Yoon, Ioana Bica, Zhaozhi Qian, Ari Ercole

Robust Curriculum Learning: from clean label detection to noisy label self-correction

Tianyi Zhou, Shengjie Wang, Jeff Bilmes

Balancing Constraints and Rewards with Meta-Gradient D4PG

Dan A. Calian, Daniel J Mankowitz, Tom Zahavy, Zhongwen Xu, Junhyuk Oh

A unifying view on implicit bias in training linear neural networks

Chulhee Yun, Shankar Krishnan, Hossein Mobahi

Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective

Muhammet Balcilar, Guillaume Renton, Pierre Héroux, Benoit Gaüzère, Sébastien Adam

Lossless Compression of Structured Convolutional Models via Lifting

Gustav Sourek, Filip Zelezny, Ondrej Kuzelka

Transient Non-stationarity and Generalisation in Deep Reinforcement Learning

Maximilian Igl, Gregory Farquhar, Jelena Luketina, Wendelin Boehmer, Shimon Whiteson

On the Origin of Implicit Regularization in Stochastic Gradient Descent

Samuel L Smith, Benoit Dherin, David Barrett, Soham De

Improving Transformation Invariance in Contrastive Representation Learning

Adam Foster, Rattana Pukdee, Tom Rainforth

Is Attention Better Than Matrix Decomposition?

Zhengyang Geng, Meng-Hao Guo, Hongxu Chen, Xia Li, Ke Wei

Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders

Mangal Prakash, Alexander Krull, Florian Jug

IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression

Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby, Tim Salimans

Learning Value Functions in Deep Policy Gradients using Residual Variance

Yannis Flet-Berliac, Reda Ouhamma, Odalric-ambrym Maillard, Philippe Preux

Set Prediction without Imposing Structure as Conditional Density Estimation

David W Zhang, Gertjan J. Burghouts, Cees G. M. Snoek

Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?

Balázs Kégl, Gabriel Hurtado, Albert Thomas

Generalized Multimodal ELBO

Thomas M. Sutter, Imant Daunhawer, Julia E Vogt

Language-Agnostic Representation Learning of Source Code from Structure and Context

Daniel Zügner, Tobias Kirschstein, Michele Catasta, Jure Leskovec, Stephan Günnemann

Representation learning for improved interpretability and classification accuracy of clinical factors from EEG

Garrett Honke, Irina Higgins, Nina Thigpen, Vladimir Miskovic, Katie Link

Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections

Csaba Toth, Patric Bonnier, Harald Oberhauser