ICML

Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios

Ugo Lecerf, Christelle Yemdji-Tchassi, Sébastien Aubert, Pietro Michiardi

Comments To appear in proceedings of International Conference on Machine Learning Technologies (ICMLT) 2022

Domain Adaptation with Factorizable Joint Shift

Hao He, Yuzhe Yang, Hao Wang

Comments 6 pages, 5 figures, ICML 2021 Workshop

Mandoline: Model Evaluation under Distribution Shift

Mayee Chen, Karan Goel, Nimit S. Sohoni, Fait Poms, Kayvon Fatahalian, Christopher Ré

Comments 33 pages. Published as a conference paper at ICML 2021

Training Graph Neural Networks with 1000 Layers

Guohao Li, Matthias Müller, Bernard Ghanem, Vladlen Koltun

Comments Accepted at ICML'2021. Code available at https://www.deepgcns.org/arch/gnn1000. Work done during Guohao Li's internship at Intel Intelligent Systems Lab. Revised reference in v3

Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement

Andrew Slavin Ross, Finale Doshi-Velez

Comments ICML 2021 paper, fixed incorrect version upload

Contrastive Learning Inverts the Data Generating Process

Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel

Comments Presented at ICML 2021. The first three authors, as well as the last two authors, contributed equally. Code is available at https://brendel-group.github.io/cl-ica

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More

Johannes Gasteiger, Marten Lienen, Stephan Günnemann

Comments Published as a conference paper at ICML 2021. Author name changed from Johannes Klicpera to Johannes Gasteiger

Model-Free and Model-Based Policy Evaluation when Causality is Uncertain

David Bruns-Smith

Comments International Conference on Machine Learning. PMLR, 2021

Approximate Group Fairness for Clustering

Bo Li, Lijun Li, Ankang Sun, Chenhao Wang, Yingfan Wang

Comments Appears in ICML 2021

Generative Adversarial Transformers

Drew A. Hudson, C. Lawrence Zitnick

Comments Published as a conference paper at ICML 2021

Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library

Yangyang Hu, Yang Yu

Comments Appeared in ICML 2020 Workshop on Bridge Between Perception and Reasoning: Graph Neural Networks & Beyond, Vienna, Austria, 2020. Code at https://agit.ai/Polixir/ABL-Sym | Video presentation available at https://slideslive.com/s/yangyang-hu-38188 | Online demonstration available at http://math.polixir.ai

Tighter expected generalization error bounds via Wasserstein distance

Borja Rodríguez-Gálvez, Germán Bassi, Ragnar Thobaben, Mikael Skoglund

Comments 29 pages: 9 of the main text, 3 of references, and 17 of appendices. Presented at ITR3 at ICML 2021. Accepted at NeurIPS 2021

Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training

Theodoros Tsiligkaridis, Jay Roberts

Comments IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022. Preliminary version ICML 2021 Adversarial Machine Learning Workshop. Code: https://github.com/TheoT1/FW-AT-Adapt

Generalisation error in learning with random features and the hidden manifold model

Federica Gerace, Bruno Loureiro, Florent Krzakala, Marc Mézard, Lenka Zdeborová

Comments v2: ICML 2020 camera-ready

Journal ref J. Stat. Mech. 2021 124013 & ICML 2020

Kernel-Based Reinforcement Learning: A Finite-Time Analysis

Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta, Emilie Kaufmann, Michal Valko

Comments Update following the publication in ICML 2021, including fixed typos

Learning Objective Boundaries for Constraint Optimization Problems

Helge Spieker, Arnaud Gotlieb

Comments The 6th International Conference on machine Learning, Optimization and Data science - LOD 2020

Journal ref In: Nicosia G. et al. (eds) Machine Learning, Optimization, and Data Science. LOD 2020. Lecture Notes in Computer Science, vol 12566. Springer, Cham

MicroRacer: a didactic environment for Deep Reinforcement Learning

Andrea Asperti, Marco Del Brutto

Comments Article submitted to the 8th International Conference on Machine Learning, Optimization, and Data Science, September 18-22, 2022, Certosa di Pontignano, Siena Tuscany, Italy

Explaining Reinforcement Learning Policies through Counterfactual Trajectories

Julius Frost, Olivia Watkins, Eric Weiner, Pieter Abbeel, Trevor Darrell, Bryan Plummer, Kate Saenko

Comments Accepted at ICML HILL 2021 Workshop

Optimal Thompson Sampling strategies for support-aware CVaR bandits

Dorian Baudry, Romain Gautron, Emilie Kaufmann, Odalric-Ambryn Maillard

Comments Presented at the Thirty-eighth International Conference on Machine Learning (ICML 2021). In this version we refine Lemma 2 and correct its proof (does not change the main theorems)

Zonotope hit-and-run for efficient sampling from projection DPPs

Guillaume Gautier, Rémi Bardenet, Michal Valko

Comments 12 pages, 12 figures, 2 columns, accepted to ICML 2017

Journal ref Proceedings of the 34th International Conference on Machine Learning 70 (2017) 1223-1232

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning

Yuhuai Wu, Markus Rabe, Wenda Li, Jimmy Ba, Roger Grosse, Christian Szegedy

Comments Published as a conference paper at ICML 2021 (16 pages)

Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks

Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

Comments Accepted at the International Conference on Machine Learning (ICML) Workshop on Uncertainty and Robustness in Deep Learning (UDL) 2020

Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks

Nezihe Merve Gürel, Xiangyu Qi, Luka Rimanic, Ce Zhang, Bo Li

Comments International Conference on Machine Learning 2021, 37 pages, 8 figures, 9 tables

Bayesian Deep Learning via Subnetwork Inference

Erik Daxberger, Eric Nalisnick, James Urquhart Allingham, Javier Antorán, José Miguel Hernández-Lobato

Comments ICML 2021; 22 pages, extended version with supplementary material

Cascaded Classifier for Pareto-Optimal Accuracy-Cost Trade-Off Using off-the-Shelf ANNs

Cecilia Latotzke, Johnson Loh, Tobias Gemmeke

Comments The final accepted publication was presented on the 7th International Conference on Machine Learning, Optimization, Data Science (LOD), October 4 - 8, 2021 in Grasmere, Lake District, England

Optimal approximation for unconstrained non-submodular minimization

Marwa El Halabi, Stefanie Jegelka

Journal ref Proceedings of the 37 th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020

Federated Learning with Buffered Asynchronous Aggregation

John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Malek, Dzmitry Huba

Comments Accepted at AISTATS 2022. Previously accepted at FL-ICML 2021

Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach

Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Junchi Yan, Hongyuan Zha

Comments ICML 2021

Generalization Guarantees for Neural Architecture Search with Train-Validation Split

Samet Oymak, Mingchen Li, Mahdi Soltanolkotabi

Comments ICML 2021

Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Pooling

Jonas Dippel, Steffen Vogler, Johannes Höhne

Comments ICML 2021 Workshop: Self-Supervised Learning for Reasoning and Perception