Geodesically convex M-estimation in metric spaces

arXiv2305.03215MaRDI QIDQ6435429FDOQ6435429

Authors: Victor-Emmanuel Brunel 

Publication date: 4 May 2023

Abstract: We study the asymptotic properties of geodesically convex $M$-estimation on non-linear spaces. Namely, we prove that under very minimal assumptions besides geodesic convexity of the cost function, one can obtain consistency and asymptotic normality, which are fundamental properties in statistical inference. Our results extend the Euclidean theory of convex $M$-estimation; They also generalize limit theorems on non-linear spaces which, essentially, were only known for barycenters, allowing to consider robust alternatives that are defined through non-smooth $M$-estimation procedures.

Mathematics Subject Classification ID

Statistics on metric spaces (62R20) Statistics on manifolds (62R30)

This page was built for publication: Geodesically convex $M$-estimation in metric spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6435429)