ICLR

PAC-Bayes Information Bottleneck

Zifeng Wang, Shao-Lun Huang, Ercan E. Kuruoglu, Jimeng Sun, Xi Chen, Yefeng Zheng

Comments ICLR'22 (Spotlight)

Effective Model Sparsification by Scheduled Grow-and-Prune Methods

Xiaolong Ma, Minghai Qin, Fei Sun, Zejiang Hou, Kun Yuan, Yi Xu, Yanzhi Wang, Yen-Kuang Chen, Rong Jin, Yuan Xie

Comments ICLR 2022 camera ready

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration

Zi-Ming Wang, Nan Xue, Ling Lei, Gui-Song Xia

Journal ref ICLR 2022

Is Importance Weighting Incompatible with Interpolating Classifiers?

Ke Alexander Wang, Niladri S. Chatterji, Saminul Haque, Tatsunori Hashimoto

Comments International Conference on Learning Representations (ICLR), 2022

Chunked Autoregressive GAN for Conditional Waveform Synthesis

Max Morrison, Rithesh Kumar, Kundan Kumar, Prem Seetharaman, Aaron Courville, Yoshua Bengio

Comments Published as a conference paper at ICLR 2022

On-Policy Model Errors in Reinforcement Learning

Lukas P. Fröhlich, Maksym Lefarov, Melanie N. Zeilinger, Felix Berkenkamp

Comments Published at The Tenth International Conference on Learning Representations (ICLR 2022)

On Improving Adversarial Transferability of Vision Transformers

Muzammal Naseer, Kanchana Ranasinghe, Salman Khan, Fahad Shahbaz Khan, Fatih Porikli

Comments ICLR'22 (Spotlight), the first two authors contributed equally. Code: https://t.ly/hBbW

Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?

Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina, Sihui Dai, Chong Xiang, Mung Chiang, Prateek Mittal

Comments ICLR 2022 version (30 pages, 13 figures, 12 tables)

Information Gain Propagation: a new way to Graph Active Learning with Soft Labels

Wentao Zhang, Yexin Wang, Zhenbang You, Meng Cao, Ping Huang, Jiulong Shan, Zhi Yang, Bin Cui

Comments 17 pages, 7 figures

Journal ref ICLR 2022

How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data

Zhiyuan Zhang, Lingjuan Lyu, Weiqiang Wang, Lichao Sun, Xu Sun

Comments Accepted by ICLR 2022

Semi-relaxed Gromov-Wasserstein divergence with applications on graphs

Cédric Vincent-Cuaz, Rémi Flamary, Marco Corneli, Titouan Vayer, Nicolas Courty

Comments Published as a conference paper at ICLR 2022

Weighted Training for Cross-Task Learning

Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J. Su

Comments Published as a conference paper at ICLR 2022

The Spectral Bias of Polynomial Neural Networks

Moulik Choraria, Leello Tadesse Dadi, Grigorios Chrysos, Julien Mairal, Volkan Cevher

Comments Accepted at the International Conference on Learning Representations(ICLR) 2022

Measuring CLEVRness: Blackbox testing of Visual Reasoning Models

Spyridon Mouselinos, Henryk Michalewski, Mateusz Malinowski

Comments ICLR 2022

Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning

Seanie Lee, Hae Beom Lee, Juho Lee, Sung Ju Hwang

Comments ICLR 2022

MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics

Kunhao Zheng, Jesse Michael Han, Stanislas Polu

Comments Published as a conference paper at ICLR 2022

It Takes Two to Tango: Mixup for Deep Metric Learning

Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, Laurent Amsaleg, Konstantinos Karantzalos, Yannis Avrithis

Comments Accepted to ICLR 2022

Relational Surrogate Loss Learning

Tao Huang, Zekang Li, Hua Lu, Yong Shan, Shusheng Yang, Yang Feng, Fei Wang, Shan You, Chang Xu

Comments Accepted to ICLR 2022

Auto-scaling Vision Transformers without Training

Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou

Comments ICLR 2022 accepted

Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect

Yuqing Wang, Minshuo Chen, Tuo Zhao, Molei Tao

Comments 45 pages

Journal ref ICLR 2022

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization

Lixu Wang, Shichao Xu, Ruiqi Xu, Xiao Wang, Qi Zhu

Comments ICLR 2022 Oral Paper

Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

Dacheng Yin, Xuanchi Ren, Chong Luo, Yuwang Wang, Zhiwei Xiong, Wenjun Zeng

Comments Accepted to ICLR 2022. Project page at https://ydcustc.github.io/retriever-demo/

Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps

Nico Courts, Henry Kvinge

Comments Accepted for publication at ICLR 2022; 19 pages

Long Expressive Memory for Sequence Modeling

T. Konstantin Rusch, Siddhartha Mishra, N. Benjamin Erichson, Michael W. Mahoney

Comments ICLR 2022

Efficient Neural Causal Discovery without Acyclicity Constraints

Phillip Lippe, Taco Cohen, Efstratios Gavves

Comments Published as a conference paper at the International Conference on Learning Representations (ICLR), 2022

Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning

Chenjia Bai, Lingxiao Wang, Zhuoran Yang, Zhihong Deng, Animesh Garg, Peng Liu, Zhaoran Wang

Comments ICLR 2022

Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, Percy Liang

Comments ICLR (Oral) 2022

Charformer: Fast Character Transformers via Gradient-based Subword Tokenization

Yi Tay, Vinh Q. Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung, Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, Donald Metzler

Comments ICLR 2022 Camera Ready

Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

Sihyun Yu, Jihoon Tack, Sangwoo Mo, Hyunsu Kim, Junho Kim, Jung-Woo Ha, Jinwoo Shin

Comments ICLR 2022. Project page with videos and code: https://sihyun-yu.github.io/digan/

Interacting Contour Stochastic Gradient Langevin Dynamics

Wei Deng, Siqi Liang, Botao Hao, Guang Lin, Faming Liang

Comments ICLR 2022