ICML

Zeroth-Order Topological Insights into Iterative Magnitude Pruning

Aishwarya Balwani, Jakob Krzyston

Comments Presented (with proceedings) at ICML 2022 Workshop on Topology, Algebra, and Geometry in Machine Learning. 16 pages, 5 figures

Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning

Harley Wiltzer, David Meger, Marc G. Bellemare

Comments Proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022

Dynamic Split Computing for Efficient Deep Edge Intelligence

Arian Bakhtiarnia, Nemanja Milošević, Qi Zhang, Dragana Bajović, Alexandros Iosifidis

Comments Accepted by the 2022 International Conference on Machine Learning (ICML 2022) DyNN Workshop

Toward Compositional Generalization in Object-Oriented World Modeling

Linfeng Zhao, Lingzhi Kong, Robin Walters, Lawson L. S. Wong

Comments ICML 2022 Long Presentation. Website: http://lfzhao.com/oowm/

Sketching Algorithms and Lower Bounds for Ridge Regression

Praneeth Kacham, David P. Woodruff

Comments To appear at ICML 2022

Reinforcement Learning with Action-Free Pre-Training from Videos

Younggyo Seo, Kimin Lee, Stephen James, Pieter Abbeel

Comments International Conference on Machine Learning (ICML 2022). Project page: https://sites.google.com/view/rl-apv

The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention

Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber

Comments Two first authors. Accepted to ICML 2022

A Modern Self-Referential Weight Matrix That Learns to Modify Itself

Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber

Comments Accepted to ICML 2022

PINs: Progressive Implicit Networks for Multi-Scale Neural Representations

Zoe Landgraf, Alexander Sorkine Hornung, Ricardo Silveira Cabral

Comments ICML 2022 (spotlight)

Modeling Structure with Undirected Neural Networks

Tsvetomila Mihaylova, Vlad Niculae, André F. T. Martins

Comments ICML 2022

Adversarial Attack and Defense for Non-Parametric Two-Sample Tests

Xilie Xu, Jingfeng Zhang, Feng Liu, Masashi Sugiyama, Mohan Kankanhalli

Comments Accepted by ICML 2022

Optimizing Sequential Experimental Design with Deep Reinforcement Learning

Tom Blau, Edwin V. Bonilla, Iadine Chades, Amir Dezfouli

Journal ref International Conference on Machine Learning (2022)

Achieving Fairness at No Utility Cost via Data Reweighing with Influence

Peizhao Li, Hongfu Liu

Comments To appear in ICML 2022

ROCK: Causal Inference Principles for Reasoning about Commonsense Causality

Jiayao Zhang, Hongming Zhang, Weijie J. Su, Dan Roth

Comments To appear, ICML 2022

Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism

Siqi Miao, Miaoyuan Liu, Pan Li

Comments Accepted to ICML 2022

Generative Coarse-Graining of Molecular Conformations

Wujie Wang, Minkai Xu, Chen Cai, Benjamin Kurt Miller, Tess Smidt, Yusu Wang, Jian Tang, Rafael Gómez-Bombarelli

Comments 23 pages, 11 figures

Journal ref International Conference on Machine Learning (ICML), 2022

Constrained Variational Policy Optimization for Safe Reinforcement Learning

Zuxin Liu, Zhepeng Cen, Vladislav Isenbaev, Wei Liu, Zhiwei Steven Wu, Bo Li, Ding Zhao

Comments ICML 2022. 25 pages

Decision-Focused Learning: Through the Lens of Learning to Rank

Jayanta Mandi, Víctor Bucarey, Maxime Mulamba, Tias Guns

Comments Accepted for presentation at ICML, 2022

Personalized Federated Learning through Local Memorization

Othmane Marfoq, Giovanni Neglia, Laetitia Kameni, Richard Vidal

Comments 23 pages, ICML 2022

Label-Descriptive Patterns and Their Application to Characterizing Classification Errors

Michael Hedderich, Jonas Fischer, Dietrich Klakow, Jilles Vreeken

Comments Accepted at ICML 2022

Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective

Jingzhao Zhang, Haochuan Li, Suvrit Sra, Ali Jadbabaie

Journal ref ICML 2022

Distinguishing rule- and exemplar-based generalization in learning systems

Ishita Dasgupta, Erin Grant, Thomas L. Griffiths

Comments To appear at the 39th International Conference on Machine Learning (ICML 2022)

Conditional GANs with Auxiliary Discriminative Classifier

Liang Hou, Qi Cao, Huawei Shen, Siyuan Pan, Xiaoshuang Li, Xueqi Cheng

Comments ICML 2022

Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets

Baojian Zhou, Yifan Sun

Comments 35 pages, 11 figures

Journal ref ICML, 2022

Feature and Parameter Selection in Stochastic Linear Bandits

Ahmadreza Moradipari, Berkay Turan, Yasin Abbasi-Yadkori, Mahnoosh Alizadeh, Mohammad Ghavamzadeh

Journal ref International Conference on Machine Learning, 2022

Sanity Simulations for Saliency Methods

Joon Sik Kim, Gregory Plumb, Ameet Talwalkar

Comments Accepted to International Conference on Machine Learning (ICML 2022)

Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity

Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie

Journal ref ICML 2022

Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations

Nabeel Seedat, Fergus Imrie, Alexis Bellot, Zhaozhi Qian, Mihaela van der Schaar

Comments Presented at the International Conference on Machine Learning (ICML) 2022

Functional Output Regression with Infimal Convolution: Exploring the Huber and $ε$-insensitive Losses

Alex Lambert, Dimitri Bouche, Zoltan Szabo, Florence d'Alché-Buc

Comments 24 pages, ICML 2022

A Closer Look at Smoothness in Domain Adversarial Training

Harsh Rangwani, Sumukh K Aithal, Mayank Mishra, Arihant Jain, R. Venkatesh Babu

Comments ICML 2022. Code: https://github.com/val-iisc/SDAT