Generalization in the Face of Adaptivity: A Bayesian Perspective

arXiv:2106.10761v3 Announce Type: replace
Abstract: Repeated use of a data sample via adaptively chosen queries can rapidly lead to overfitting, wherein the empirical evaluation of queries on the sample significantly deviates from their mean with respect to the underlying data distribution. It turns out that simple noise addition algorithms suffice to prevent this issue, and differential privacy-based analysis of these algorithms shows that they can handle an asymptotically optimal number of queries. However, differential privacy's worst-case nature entails scaling such …

abstract algorithms arxiv bayesian cs.lg data distribution evaluation face mean noise overfitting perspective queries sample simple stat.ml type via