ICML

Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?

Anna-Kathrin Kopetzki, Bertrand Charpentier, Daniel Zügner, Sandhya Giri, Stephan Günnemann

Comments Published at ICML 2021

A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network

Jun-Kun Wang, Chi-Heng Lin, Jacob Abernethy

Comments Accepted at ICML 2021

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

Tianle Cai, Shengjie Luo, Keyulu Xu, Di He, Tie-Yan Liu, Liwei Wang

Comments ICML 2021, Code: https://github.com/lsj2408/GraphNorm

Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies

Uthsav Chitra, Kimberly Ding, Jasper C. H. Lee, Benjamin J. Raphael

Comments Accepted to ICML 2021

Guarantees for Tuning the Step Size using a Learning-to-Learn Approach

Xiang Wang, Shuai Yuan, Chenwei Wu, Rong Ge

Comments ICML 2021. Added proof sketch

Compositional Video Synthesis with Action Graphs

Amir Bar, Roei Herzig, Xiaolong Wang, Anna Rohrbach, Gal Chechik, Trevor Darrell, Amir Globerson

Comments ICML 2021 Camera Ready

Neural Architecture Search without Training

Joseph Mellor, Jack Turner, Amos Storkey, Elliot J. Crowley

Comments Accepted at ICML 2021 for a long presentation

Revealing the Structure of Deep Neural Networks via Convex Duality

Tolga Ergen, Mert Pilanci

Comments Accepted to ICML 2021

What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?

Weijian Deng, Stephen Gould, Liang Zheng

Comments ICML 2021 camera ready

Matrix Completion with Model-free Weighting

Jiayi Wang, Raymond K. W. Wong, Xiaojun Mao, Kwun Chuen Gary Chan

Comments Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method

Peng Wang, Huikang Liu, Zirui Zhou, Anthony Man-Cho So

Comments This paper has been accepted to ICML 2021

Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time

Laxman Dhulipala, David Eisenstat, Jakub Łącki, Vahab Mirrokni, Jessica Shi

Comments This is the full version of the paper appearing in ICML'21

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings

Matthias Fey, Jan E. Lenssen, Frank Weichert, Jure Leskovec

Comments Published as a conference paper at ICML 2021

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline

Ankit Goyal, Hei Law, Bowei Liu, Alejandro Newell, Jia Deng

Comments Accepted to ICML 2021

Explaining Time Series Predictions with Dynamic Masks

Jonathan Crabbé, Mihaela van der Schaar

Comments Presented at the Thirty-eighth International Conference on Machine Learning (ICML 2021)

Operationalizing Complex Causes: A Pragmatic View of Mediation

Limor Gultchin, David S. Watson, Matt J. Kusner, Ricardo Silva

Journal ref International Conference on Machine Learning 2021

Vector Quantized Models for Planning

Sherjil Ozair, Yazhe Li, Ali Razavi, Ioannis Antonoglou, Aäron van den Oord, Oriol Vinyals

Comments ICML 2021

Scaling Properties of Deep Residual Networks

Alain-Sam Cohen, Rama Cont, Alain Rossier, Renyuan Xu

Comments Published at ICML 2021

Data-Free Knowledge Distillation for Heterogeneous Federated Learning

Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Relative Positional Encoding for Transformers with Linear Complexity

Antoine Liutkus, Ondřej Cífka, Shih-Lun Wu, Umut Şimşekli, Yi-Hsuan Yang, Gaël Richard

Comments ICML 2021 (long talk) camera-ready. 24 pages

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

Angelos Filos, Clare Lyle, Yarin Gal, Sergey Levine, Natasha Jaques, Gregory Farquhar

Comments The last two authors contributed equally. Accepted at ICML 2021

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed

Maria Refinetti, Sebastian Goldt, Florent Krzakala, Lenka Zdeborová

Comments The accompanying code for this paper is available at https://github.com/mariaref/rfvs2lnn_GMM_online

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Dataset Condensation with Differentiable Siamese Augmentation

Bo Zhao, Hakan Bilen

Journal ref International Conference on Machine Learning 2021

AlphaNet: Improved Training of Supernets with Alpha-Divergence

Dilin Wang, Chengyue Gong, Meng Li, Qiang Liu, Vikas Chandra

Comments International Conference on Machine Learning (ICML) 2021

Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with $\mathcal{O}(1/k^2)$ Rate on Squared Gradient Norm

TaeHo Yoon, Ernest K. Ryu

Comments Published at ICML 2021 as a long talk

Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces

Xingchen Wan, Vu Nguyen, Huong Ha, Binxin Ru, Cong Lu, Michael A. Osborne

Comments ICML 2021. 9 page, 6 figures (26 pages, 16 figures, 2 tables including references and appendices)

Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness

Vien V. Mai, Mikael Johansson

Comments ICML-2021

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

Wonjae Kim, Bokyung Son, Ildoo Kim

Comments ICML 2021 Long Presentation

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei Zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao Gao, Haitao Long, Quan Yuan

Comments ICML 2021 camera ready

Align, then memorise: the dynamics of learning with feedback alignment

Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt

Comments The accompanying code for this paper is available at https://github.com/sdascoli/dfa-dynamics

Journal ref Proceedings of the 38th International Conference on Machine Learning (ICML), PMLR 139, 2021