English

A Finer Calibration Analysis for Adversarial Robustness

Machine Learning 2021-05-07 v2 Machine Learning

Abstract

We present a more general analysis of HH-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 HH-consistency results covering common hypothesis sets.

Keywords

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

R2 v1 2026-06-24T01:46:19.173Z