Lipschitz Continuity of Mahalanobis Distances and Bilinear Forms

Marc Sebban, Valentina Zantedeschi, Rémi Emonet

Abstract: Many theoretical results in the machine learning domain stand only for functions that are Lipschitz continuous. Lipschitz continuity is a strong form of continuity that linearly bounds the variations of a function. In this paper, we derive tight Lipschitz constants for two families of metrics: Mahalanobis distances and bounded-space bilinear forms. To our knowledge, this is the first time the Mahalanobis distance is formally proved to be Lipschitz continuous and that such tight Lipschitz constants are derived.

This page was built for publication: Lipschitz Continuity of Mahalanobis Distances and Bilinear Forms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6511683)