ICML

Variational Auto-Regressive Gaussian Processes for Continual Learning

Sanyam Kapoor, Theofanis Karaletsos, Thang D. Bui

Comments International Conference on Machine Learning (ICML), 2021

Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning

Shariq Iqbal, Christian A. Schroeder de Witt, Bei Peng, Wendelin Böhmer, Shimon Whiteson, Fei Sha

Comments ICML 2021 Camera Ready

Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving

Yang Song, Chenlin Meng, Renjie Liao, Stefano Ermon

Comments ICML 2021

Event Outlier Detection in Continuous Time

Siqi Liu, Milos Hauskrecht

Comments ICML 2021 camera-ready

K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets

Xiu Su, Shan You, Mingkai Zheng, Fei Wang, Chen Qian, Changshui Zhang, Chang Xu

Comments Accepted by ICML 2021

Neural Symbolic Regression that Scales

Luca Biggio, Tommaso Bendinelli, Alexander Neitz, Aurelien Lucchi, Giambattista Parascandolo

Comments Accepted at the 38th International Conference on Machine Learning (ICML) 2021

DORO: Distributional and Outlier Robust Optimization

Runtian Zhai, Chen Dan, J. Zico Kolter, Pradeep Ravikumar

Comments ICML 2021. Codes: https://github.com/RuntianZ/doro

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

Daochen Zha, Jingru Xie, Wenye Ma, Sheng Zhang, Xiangru Lian, Xia Hu, Ji Liu

Comments Accepted by ICML 2021

Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Jaehyeon Kim, Jungil Kong, Juhee Son

Comments ICML 2021

Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix

Maximilian Lam, Gu-Yeon Wei, David Brooks, Vijay Janapa Reddi, Michael Mitzenmacher

Comments ICML 2021

RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting

Soumyasundar Pal, Liheng Ma, Yingxue Zhang, Mark Coates

Comments ICML 2021

Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation

Jiawei Zhang, Linyi Li, Huichen Li, Xiaolu Zhang, Shuang Yang, Bo Li

Comments ICML 2021

Adversarial purification with Score-based generative models

Jongmin Yoon, Sung Ju Hwang, Juho Lee

Comments ICML 2021

Modeling Hierarchical Structures with Continuous Recursive Neural Networks

Jishnu Ray Chowdhury, Cornelia Caragea

Comments Accepted in ICML 2021 (long talk)

Adversarial Option-Aware Hierarchical Imitation Learning

Mingxuan Jing, Wenbing Huang, Fuchun Sun, Xiaojian Ma, Tao Kong, Chuang Gan, Lei Li

Comments accepted by ICML 2021

ChaCha for Online AutoML

Qingyun Wu, Chi Wang, John Langford, Paul Mineiro, Marco Rossi

Comments 16 pages (including supplementary appendix). Appearing at ICML 2021

Journal ref ICML 2021

Dynamic Game Theoretic Neural Optimizer

Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou

Comments Accepted in International Conference on Machine Learning (ICML) 2021 as Oral

Improved, Deterministic Smoothing for L_1 Certified Robustness

Alexander Levine, Soheil Feizi

Comments ICML 2021 Accepted Paper

Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design

Adam Foster, Desi R. Ivanova, Ilyas Malik, Tom Rainforth

Comments Published as a conference paper at ICML 2021

Adapting to Misspecification in Contextual Bandits with Offline Regression Oracles

Sanath Kumar Krishnamurthy, Vitor Hadad, Susan Athey

Comments ICML 2021

Calibrate Before Use: Improving Few-Shot Performance of Language Models

Tony Z. Zhao, Eric Wallace, Shi Feng, Dan Klein, Sameer Singh

Comments ICML 2021

Leveraging Public Data for Practical Private Query Release

Terrance Liu, Giuseppe Vietri, Thomas Steinke, Jonathan Ullman, Zhiwei Steven Wu

Comments ICML 2021

Learning Intra-Batch Connections for Deep Metric Learning

Jenny Seidenschwarz, Ismail Elezi, Laura Leal-Taixé

Comments Accepted to International Conference on Machine Learning (ICML) 2021, includes non-archival supplementary material

Multi-Task Reinforcement Learning with Context-based Representations

Shagun Sodhani, Amy Zhang, Joelle Pineau

Comments Accepted at the 38th International Conference on Machine Learning (ICML 2021). 17 pages, 4 figures, 20 tables

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yunhsuan Sung, Zhen Li, Tom Duerig

Comments ICML 2021

Journal ref International Conference on Machine Learning 2021

On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths

Quynh Nguyen

Comments ICML 2021

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization

Stanislaw Jastrzebski, Devansh Arpit, Oliver Astrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof Geras

Comments The last two authors contributed equally. Accepted to the International Conference on Machine Learning 2021

Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent

Kangqiao Liu, Liu Ziyin, Masahito Ueda

Comments Camera-ready version for the Thirty-eighth International Conference on Machine Learning (ICML 2021). 12 + 14 pages, 6 + 3 figures, 1 + 0 table. *First two authors contributed equally

Value Alignment Verification

Daniel S. Brown, Jordan Schneider, Anca D. Dragan, Scott Niekum

Comments In proceedings International Conference on Machine Learning (ICML) 2021

Improved Contrastive Divergence Training of Energy Based Models

Yilun Du, Shuang Li, Joshua Tenenbaum, Igor Mordatch

Comments ICML 2021, Project webpage at https://energy-based-model.github.io/improved-contrastive-divergence