ICLR

Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View

Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng

Comments Accepted to ICLR 2022. Source code: https://github.com/xrenaa/DisCo

Mastering Atari with Discrete World Models

Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, Jimmy Ba

Comments Published at ICLR 2021. Website: https://danijar.com/dreamerv2

Deconstructing the Inductive Biases of Hamiltonian Neural Networks

Nate Gruver, Marc Finzi, Samuel Stanton, Andrew Gordon Wilson

Comments ICLR 2022. Code available at https://github.com/ngruver/decon-hnn

Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality

Daniel Watson, William Chan, Jonathan Ho, Mohammad Norouzi

Comments Published as a conference paper at ICLR 2022

Domain Adversarial Training: A Game Perspective

David Acuna, Marc T Law, Guojun Zhang, Sanja Fidler

Comments ICLR 2022

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

Yash Mehta, Colin White, Arber Zela, Arjun Krishnakumar, Guri Zabergja, Shakiba Moradian, Mahmoud Safari, Kaicheng Yu, Frank Hutter

Comments ICLR 2022

Sparse Communication via Mixed Distributions

António Farinhas, Wilker Aziz, Vlad Niculae, André F. T. Martins

Comments Accepted for oral presentation at ICLR 2022

ProMP: Proximal Meta-Policy Search

Jonas Rothfuss, Dennis Lee, Ignasi Clavera, Tamim Asfour, Pieter Abbeel

Comments The first three authors contributed equally. Published at ICLR 2019

F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization

Qing Jin, Jian Ren, Richard Zhuang, Sumant Hanumante, Zhengang Li, Zhiyu Chen, Yanzhi Wang, Kaiyuan Yang, Sergey Tulyakov

Comments ICLR 2022 (Oral)

Graph Neural Networks with Learnable Structural and Positional Representations

Vijay Prakash Dwivedi, Anh Tuan Luu, Thomas Laurent, Yoshua Bengio, Xavier Bresson

Comments Code at https://github.com/vijaydwivedi75/gnn-lspe

Journal ref ICLR 2022 (https://openreview.net/pdf?id=wTTjnvGphYj)

Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective

Luca Scimeca, Seong Joon Oh, Sanghyuk Chun, Michael Poli, Sangdoo Yun

Comments To be published in "The International Conference on Learning Representations" (ICLR 2022)(Accepted) First two authors have contributed equally

Disentanglement Analysis with Partial Information Decomposition

Seiya Tokui, Issei Sato

Comments ICLR 2022

Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks

Andrea Cini, Ivan Marisca, Cesare Alippi

Comments Accepted at ICLR 2022

Dealing with Non-Stationarity in MARL via Trust-Region Decomposition

Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, Hongyuan Zha

Comments 39 pages, 23 figures, ICLR 2022 Camera Ready

Learning Temporally Causal Latent Processes from General Temporal Data

Weiran Yao, Yuewen Sun, Alex Ho, Changyin Sun, Kun Zhang

Comments ICLR 2022: https://openreview.net/forum?id=RDlLMjLJXdq

Unifying Likelihood-free Inference with Black-box Optimization and Beyond

Dinghuai Zhang, Jie Fu, Yoshua Bengio, Aaron Courville

Comments ICLR 2022 spotlight

Universal Approximation Under Constraints is Possible with Transformers

Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanić

Comments 9.5 Pages + 14 Page Append + References, 3 Tables, 5 Figures

Journal ref ICLR 2022 (Spotlight)

Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations

Weiqi Peng, Jinghui Chen

Comments Accepted at ICLR 2022

Backdoor Defense via Decoupling the Training Process

Kunzhe Huang, Yiming Li, Baoyuan Wu, Zhan Qin, Kui Ren

Comments This work is accepted by the ICLR 2022. The first two authors contributed equally to this work. 25 pages

BAM: Bayes with Adaptive Memory

Josue Nassar, Jennifer Brennan, Ben Evans, Kendall Lowrey

Comments International Conference on Learning Representations (ICLR), 2022

Lipschitz-constrained Unsupervised Skill Discovery

Seohong Park, Jongwook Choi, Jaekyeom Kim, Honglak Lee, Gunhee Kim

Comments Accepted to ICLR 2022

UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning

Kunchang Li, Yali Wang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao

Comments Published as a conference paper at ICLR 2022; 19pages, 7 figures

Neural Models for Output-Space Invariance in Combinatorial Problems

Yatin Nandwani, Vidit Jain, Mausam, Parag Singla

Comments Published as a conference paper at ICLR 2022

One-Shot Neural Architecture Search via Compressive Sensing

Minsu Cho, Mohammadreza Soltani, Chinmay Hegde

Comments 2nd Workshop on Neural Architecture Search at ICLR 2021

Distributionally Robust Fair Principal Components via Geodesic Descents

Hieu Vu, Toan Tran, Man-Chung Yue, Viet Anh Nguyen

Comments International Conference on Learning Representations (ICLR) 2022

TRGP: Trust Region Gradient Projection for Continual Learning

Sen Lin, Li Yang, Deliang Fan, Junshan Zhang

Comments Published as a conference paper at ICLR 2022

Learning Synthetic Environments and Reward Networks for Reinforcement Learning

Fabio Ferreira, Thomas Nierhoff, Andreas Saelinger, Frank Hutter

Journal ref International Conference on Learning Representations (ICLR 2022)

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

Shiwei Liu, Tianlong Chen, Xiaohan Chen, Li Shen, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy

Comments Published as a conference paper at ICLR 2022. Code is available at https://github.com/VITA-Group/Random_Pruning

Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach

Chunwei Ma, Ziyun Huang, Mingchen Gao, Jinhui Xu

Comments Accepted for publication in ICLR 2022; https://openreview.net/forum?id=6kCiVaoQdx9

Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?

Matthew Farrell, Blake Bordelon, Shubhendu Trivedi, Cengiz Pehlevan

Comments Version accepted to ICLR 2022