Univ. Heidelberg
Statistics Group   Institute of Applied Mathematics   Faculty of Mathematics and Computer Science   University Heidelberg
Ruprecht-Karls-Universität Heidelberg Institute of Applied Mathematics Statistics of inverse problems Research Group
german english french



Publications
Cooperations
Research projects
Events
Teaching
Completed theses
People
Contact


Last edited on
Oct 10, 2022 by JJ
.
Article:
Electronic Journal of Statistics, 13(2), 4280-4345, 2019.
dx.doi.org/10.1214/19-EJS1618

Title:
Convergence rates for the generalized Fréchet mean via the quadruple inequality

Author:
Christof Schötz

Abstract:
For sets Q and M, the generalized Fréchet mean m in Q of a random variable Y, which has values in M, is any minimizer of q->E[c(q,Y)], where c:QxM->R is a cost function. There are little restrictions to  and Q and M. In particular, Q can be a non-Euclidean metric space. We provide convergence rates for the empirical generalized Fréchet mean. Conditions for rates in probability and rates in expectation are given. In contrast to previous results on Fréchet means, we do not require a finite diameter of the Q or M. Instead, we assume an inequality, which we call quadruple inequality. It generalizes an otherwise common Lipschitz condition on the cost function. This quadruple inequality is known to hold in Hadamard spaces. We show that it also holds in a suitable way for certain powers of a Hadamard-metric.

Preliminary version:
arXiv:1812.08037

Comment / Contact
Markdown: formatting is possible. All comments are held for moderation.