ICLR

Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models

Mitch Hill, Jonathan Mitchell, Song-Chun Zhu

Comments ICLR 2021

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I Chang, Yan Xu

Comments ICLR 2021 (Spotlight). Code: https://github.com/zsyzzsoft/co-mod-gan Demo: https://comodgan.ml/

The Geometry of Deep Generative Image Models and its Applications

Binxu Wang, Carlos R. Ponce

Comments 25 pages, 11 figures. Published as a conference paper at ICLR 2021

Randomized Ensembled Double Q-Learning: Learning Fast Without a Model

Xinyue Chen, Che Wang, Zijian Zhou, Keith Ross

Comments Published as a conference paper at ICLR 2021

Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning

Rishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro, Marc G. Bellemare

Comments ICLR 2021 (Spotlight). Website: https://agarwl.github.io/pse

Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning

Xuebo Liu, Longyue Wang, Derek F. Wong, Liang Ding, Lidia S. Chao, Zhaopeng Tu

Comments Accepted to ICLR 2021

Mapping the Timescale Organization of Neural Language Models

Hsiang-Yun Sherry Chien, Jinhan Zhang, Christopher. J. Honey

Comments 23 pages, 4 main figures, 10 appendix figures; published as a conference paper at ICLR 2021

Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition

Yangming Li, Lemao Liu, Shuming Shi

Comments Accepted as a conference paper at ICLR 2021

Neural Spatio-Temporal Point Processes

Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel

Journal ref ICLR 2021

Complex Query Answering with Neural Link Predictors

Erik Arakelyan, Daniel Daza, Pasquale Minervini, Michael Cochez

Comments Proceedings of the Ninth International Conference on Learning Representations (ICLR 2021, oral presentation)

PAC Confidence Predictions for Deep Neural Network Classifiers

Sangdon Park, Shuo Li, Insup Lee, Osbert Bastani

Comments Accepted to ICLR 2021

Trajectory Prediction using Equivariant Continuous Convolution

Robin Walters, Jinxi Li, Rose Yu

Comments Accepted to ICLR 2021, 17 pages

i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning

Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, Honglak Lee

Comments ICLR 2021

How Does Mixup Help With Robustness and Generalization?

Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou

Comments Accepted by ICLR 2021, and selected as spotlight (top 6% of submissions)

Deformable DETR: Deformable Transformers for End-to-End Object Detection

Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, Jifeng Dai

Comments ICLR 2021 Oral

Meta-Learning of Structured Task Distributions in Humans and Machines

Sreejan Kumar, Ishita Dasgupta, Jonathan D. Cohen, Nathaniel D. Daw, Thomas L. Griffiths

Comments Accepted at ICLR 2021

Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction

Wei Deng, Qi Feng, Georgios Karagiannis, Guang Lin, Faming Liang

Comments Accepted by ICLR 2021

Multi-timescale Representation Learning in LSTM Language Models

Shivangi Mahto, Vy A. Vo, Javier S. Turek, Alexander G. Huth

Journal ref International Conference on Learning Representations 2021

Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS

Lin Chen, Sheng Xu

Comments Accepted to ICLR 2021

Explainable Deep One-Class Classification

Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks, Marius Kloft, Klaus-Robert Müller

Comments 25 pages, published as a conference paper at ICLR 2021

Adaptive Procedural Task Generation for Hard-Exploration Problems

Kuan Fang, Yuke Zhu, Silvio Savarese, Li Fei-Fei

Comments ICLR 2021

Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization

Kaidi Cao, Yining Chen, Junwei Lu, Nikos Arechiga, Adrien Gaidon, Tengyu Ma

Comments to appear in ICLR 2021

Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time

Tolga Ergen, Mert Pilanci

Comments Accepted for Spotlight Presentation at ICLR 2021

Journal ref International Conference on Learning Representations (ICLR), 2021

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks

Alexander Levine, Soheil Feizi

Comments ICLR 2021

Quantifying Differences in Reward Functions

Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike

Comments Published at ICLR 2021. 9 pages main paper, 42 pages total

not-MIWAE: Deep Generative Modelling with Missing not at Random Data

Niels Bruun Ipsen, Pierre-Alexandre Mattei, Jes Frellsen

Comments Camera-ready version for ICLR 2021

Tent: Fully Test-time Adaptation by Entropy Minimization

Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, Trevor Darrell

Comments ICLR 2021 Spotlight

Getting a CLUE: A Method for Explaining Uncertainty Estimates

Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández-Lobato

Comments Accepted as an oral presentation at ICLR 2021

Evaluating the Disentanglement of Deep Generative Models through Manifold Topology

Sharon Zhou, Eric Zelikman, Fred Lu, Andrew Y. Ng, Gunnar Carlsson, Stefano Ermon

Comments Published at ICLR 2021

Geometry-Aware Gradient Algorithms for Neural Architecture Search

Liam Li, Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar

Comments ICLR 2021 Camera-Ready