Gaussian-Smoothed Sliced Probability Divergences

arXiv:2404.03273v1 Announce Type: new
Abstract: Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown that it provides performances similar to its non-smoothed (non-private) counterpart. However, the computationaland statistical properties of such a metric have not yet been well-established. This work investigates the theoretical properties of this distance as well as those of generalized versions denoted as Gaussian-smoothed sliced divergences. We first show that smoothing and slicing …

abstract arxiv cs.lg data however math.st performances privacy probability statistical stat.ml stat.th type work