Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifier

Autor:	Frank, Natalie S.
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Mathematics - Statistics Theory Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Minimizing an adversarial surrogate risk is a common technique for learning robust classifiers. Prior work showed that convex surrogate losses are not statistically consistent in the adversarial context -- or in other words, a minimizing sequence of the adversarial surrogate risk will not necessarily minimize the adversarial classification error. We connect the consistency of adversarial surrogate losses to properties of minimizers to the adversarial classification risk, known as adversarial Bayes classifiers. Specifically, under reasonable distributional assumptions, a convex surrogate loss is statistically consistent for adversarial learning iff the adversarial Bayes classifier satisfies a certain notion of uniqueness. Comment: 2 figures, 20 pages, v2: fixed typos, v3: improved organization of paper and added figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2404.17358 Zobrazit plný text záznamu View this record from Arxiv