On Rate-Optimal Partitioning Classification from Observable and from Privatised Data

arXiv:2312.14889v2 Announce Type: replace-cross
Abstract: In this paper we revisit the classical method of partitioning classification and study its convergence rate under relaxed conditions, both for observable (non-privatised) and for privatised data. Let the feature vector $X$ take values in $\mathbb{R}^d$ and denote its label by $Y$. Previous results on the partitioning classifier worked with the strong density assumption, which is restrictive, as we demonstrate through simple examples. We assume that the distribution of $X$ is a mixture of an …

arxiv classification conditions convergence cs.cr cs.lg data feature math.st non observable rate results stat.ml stat.th study under