Differentially Private Worst-group Risk Minimization

arXiv:2402.19437v1 Announce Type: new
Abstract: We initiate a systematic study of worst-group risk minimization under $(\epsilon, \delta)$-differential privacy (DP). The goal is to privately find a model that approximately minimizes the maximal risk across $p$ sub-populations (groups) with different distributions, where each group distribution is accessed via a sample oracle. We first present a new algorithm that achieves excess worst-group population risk of $\tilde{O}(\frac{p\sqrt{d}}{K\epsilon} + \sqrt{\frac{p}{K}})$, where $K$ is the total number of samples drawn from all groups and $d$ …

abstract arxiv cs.ai cs.cr cs.lg delta differential differential privacy distribution epsilon oracle privacy risk sample study type via