A Finer Calibration Analysis for Adversarial Robustness
Machine Learning
2021-05-07 v2 Machine Learning
Abstract
We present a more general analysis of -calibration for adversarially robust classification. By adopting a finer definition of calibration, we can cover settings beyond the restricted hypothesis sets studied in previous work. In particular, our results hold for most common hypothesis sets used in machine learning. We both fix some previous calibration results (Bao et al., 2020) and generalize others (Awasthi et al., 2021). Moreover, our calibration results, combined with the previous study of consistency by Awasthi et al. (2021), also lead to more general -consistency results covering common hypothesis sets.
Cite
@article{arxiv.2105.01550,
title = {A Finer Calibration Analysis for Adversarial Robustness},
author = {Pranjal Awasthi and Anqi Mao and Mehryar Mohri and Yutao Zhong},
journal= {arXiv preprint arXiv:2105.01550},
year = {2021}
}
Comments
arXiv admin note: text overlap with arXiv:2104.09658