ICML

Trade-off between reconstruction loss and feature alignment for domain generalization

Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz, Shuchin Aeron

Comments 13 pages, 2 tables

Journal ref International Conference on Machine Learning and Applications (ICMLA-2022)

The Edge of Disaster: A Battle Between Autonomous Racing and Safety

Matthew Howe, James Bockman, Adrian Orenstein, Stefan Podgorski, Sam Bahrami, Ian Reid

Journal ref 1st ICML Workshop on Safe Learning for Autonomous Driving (SL4AD), 2022

NeuralEF: Deconstructing Kernels by Deep Neural Networks

Zhijie Deng, Jiaxin Shi, Jun Zhu

Comments International Conference on Machine Learning (ICML), 2022

Poolingformer: Long Document Modeling with Pooling Attention

Hang Zhang, Yeyun Gong, Yelong Shen, Weisheng Li, Jiancheng Lv, Nan Duan, Weizhu Chen

Comments Accepted by ICML 2021

Random Actions vs Random Policies: Bootstrapping Model-Based Direct Policy Search

Elias Hanna, Alex Coninx, Stéphane Doncieux

Comments ICML 2022 Workshop Adaptive Experimental Design and Active Learning in the Real World

Target-aware Molecular Graph Generation

Cheng Tan, Zhangyang Gao, Stan Z. Li

Comments Accepted by the 2nd AI4Science Workshop at the 39th International Conference on Machine Learning (ICML), 2022

Non-Vacuous Generalisation Bounds for Shallow Neural Networks

Felix Biggs, Benjamin Guedj

Comments 19 pages, 12 figures

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

Irregularly-Sampled Time Series Modeling with Spline Networks

Marin Biloš, Emanuel Ramneantu, Stephan Günnemann

Comments ICML Continuous Time Methods for Machine Learning Workshop (2022)

Not All Poisons are Created Equal: Robust Training against Data Poisoning

Yu Yang, Tian Yu Liu, Baharan Mirzasoleiman

Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:25154-25165, 2022

Average-Reward Off-Policy Policy Evaluation with Function Approximation

Shangtong Zhang, Yi Wan, Richard S. Sutton, Shimon Whiteson

Comments ICML 2021

Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization

Seungyong Moon, Gaon An, Hyun Oh Song

Comments Accepted and to appear at ICML 2019

Messing Up 3D Virtual Environments: Transferable Adversarial 3D Objects

Enrico Meloni, Matteo Tiezzi, Luca Pasqualini, Marco Gori, Stefano Melacci

Comments 8 pages, 7 figures, accepted for publication at the IEEE International Conference on Machine Learning and Applications (ICMLA) 2021

A Multistep Frank-Wolfe Method

Zhaoyue Chen, Yifan Sun

Comments 12 pages, Continuous time methods for machine learning International Conference on Machine Learning Workshop, Baltimore, Maryland, USA, 2022. arXiv admin note: substantial text overlap with arXiv:2106.05753

Brain Network Transformer

Xuan Kan, Wei Dai, Hejie Cui, Zilong Zhang, Ying Guo, Carl Yang

Comments Accepted to NeurIPS 2022. The previous version is accepted for Workshop ICML-IMLH 2022 (Oral, no proceedings)

Strong Lensing Source Reconstruction Using Continuous Neural Fields

Siddharth Mishra-Sharma, Ge Yang

Comments 9+2 pages, 3+2 figures, Spotlight at the Machine Learning for Astrophysics Workshop at ICML 2022; v2, references added

Certified Robustness Against Natural Language Attacks by Causal Intervention

Haiteng Zhao, Chang Ma, Xinshuai Dong, Anh Tuan Luu, Zhi-Hong Deng, Hanwang Zhang

Journal ref International Conference on Machine International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022

Transformer-Based Speech Synthesizer Attribution in an Open Set Scenario

Emily R. Bartusiak, Edward J. Delp

Comments Accepted to the 2022 IEEE International Conference on Machine Learning and Applications

Journal ref IEEE International Conference on Machine Learning and Applications, pp. 1-8, December 2022, Nassau, The Bahamas

Invariance-adapted decomposition and Lasso-type contrastive learning

Masanori Koyama, Takeru Miyato, Kenji Fukumizu

Journal ref 2022 ICML workshop of Topology, Algebra and Geometry in Machine Learning (spotlight)

Deep object detection for waterbird monitoring using aerial imagery

Krish Kabra, Alexander Xiong, Wenbin Li, Minxuan Luo, William Lu, Raul Garcia, Dhananjay Vijay, Jiahui Yu, Maojie Tang, Tianjiao Yu, Hank Arnold, Anna Vallery, Richard Gibbons, Arko Barman

Comments Longer version of accepted short paper at 21st IEEE International Conference on Machine Learning and Applications (ICMLA'22). 7 pages, 5 figures

MAGIC: Microlensing Analysis Guided by Intelligent Computation

Haimeng Zhao, Wei Zhu

Comments 23 pages, 19 figures, accepted version. Code available at https://github.com/JasonZHM/magic-microlensing . An earlier version of this work is accepted to the ICML 2022 Workshop on Machine Learning for Astrophysics at https://ml4astro.github.io/icml2022/

Journal ref The Astronomical Journal, 164, 192 (2022)

Optimal Auctions through Deep Learning: Advances in Differentiable Economics

Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C. Parkes, Sai Srivatsa Ravindranath

Comments An extended abstract appeared in ICML'19, along with a short Research Highlight in the Communications of the ACM

SECOE: Alleviating Sensors Failure in Machine Learning-Coupled IoT Systems

Yousef AlShehri, Lakshmish Ramaswamy

Comments 8 pages, 10 figures, Accepted as a conference paper at IEEE International Conference on Machine Learning and Applications (ICMLA 2022)

Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models

Viktor Bengs, Aadirupa Saha, Eyke Hüllermeier

Journal ref Proceedings of the 39th International Conference on Machine Learning (ICML), PMLR 162:1764-1786, 2022

Transfer Learning with Joint Fine-Tuning for Multimodal Sentiment Analysis

Guilherme Lourenço de Toledo, Ricardo Marcondes Marcacini

Comments Talk: https://icml.cc/Conferences/2022/ScheduleMultitrack?event=13483#collapse20429

What Dense Graph Do You Need for Self-Attention?

Yuxin Wang, Chu-Tak Lee, Qipeng Guo, Zhangyue Yin, Yunhua Zhou, Xuanjing Huang, Xipeng Qiu

Comments Accepted by ICML 2022. Code is available at https://github.com/yxzwang/Normalized-Information-Payload

Extended Unconstrained Features Model for Exploring Deep Neural Collapse

Tom Tirer, Joan Bruna

Comments ICML 2022. Relaxed Theorem 4.2 and clarified proofs

Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics

Arkopal Dutt, Andrey Y. Lokhov, Marc Vuffray, Sidhant Misra

Comments Accepted to ICML 2021

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2914-2925, 2021

A Functional Perspective on Learning Symmetric Functions with Neural Networks

Aaron Zweig, Joan Bruna

Comments Accepted to ICML 2021

Class-wise and reduced calibration methods

Michael Panchenko, Anes Benmerzoug, Miguel de Benito Delgado

Comments Accepted at the 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022

A General Recipe for Likelihood-free Bayesian Optimization

Jiaming Song, Lantao Yu, Willie Neiswanger, Stefano Ermon

Comments ICML 2022. This version fixes a typo in eq 33