all AI news
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition. (arXiv:2202.10103v2 [cs.LG] UPDATED)
Web: http://arxiv.org/abs/2202.10103
June 17, 2022, 1:11 a.m. | Tianyu Pang, Min Lin, Xiao Yang, Jun Zhu, Shuicheng Yan
cs.LG updates on arXiv.org arxiv.org
The trade-off between robustness and accuracy has been widely studied in the
adversarial literature. Although still controversial, the prevailing view is
that this trade-off is inherent, either empirically or theoretically. Thus, we
dig for the origin of this trade-off in adversarial training and find that it
may stem from the improperly defined robust error, which imposes an inductive
bias of local invariance -- an overcorrection towards smoothness. Given this,
we advocate employing local equivariance to describe the ideal behavior of …
More from arxiv.org / cs.LG updates on arXiv.org
Latest AI/ML/Big Data Jobs
Machine Learning Researcher - Saalfeld Lab
@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia
Project Director, Machine Learning in US Health
@ ideas42.org | Remote, US
Data Science Intern
@ NannyML | Remote
Machine Learning Engineer NLP/Speech
@ Play.ht | Remote
Research Scientist, 3D Reconstruction
@ Yembo | Remote, US
Clinical Assistant or Associate Professor of Management Science and Systems
@ University at Buffalo | Buffalo, NY