Convergence Rates for the Generalized Fréchet Mean via the Quadruple Inequality

12/19/2018
by   Christof Schötz, et al.
0

For sets Q and Y, the generalized Fréchet mean m ∈ Q of a random variable Y, which has values in Y, is any minimizer of q E[ c(q,Y)], where c Q × Y → R is a cost function. There are little restrictions to Q and Y. 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 Y. 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2018

Hanson-Wright inequality in Hilbert spaces with application to K-means clustering for non-Euclidean data

We derive a dimensional-free Hanson-Wright inequality for quadratic form...
research
04/16/2018

A refinement of Bennett's inequality with applications to portfolio optimization

A refinement of Bennett's inequality is introduced which is strictly tig...
research
12/23/2020

Strong Laws of Large Numbers for Generalizations of Fréchet Mean Sets

A Fréchet mean of a random variable Y with values in a metric space (𝒬, ...
research
10/17/2022

Ratio convergence rates for Euclidean first-passage percolation: Applications to the graph infinity Laplacian

In this paper we prove the first quantitative convergence rates for the ...
research
12/22/2022

Fréchet Mean Set Estimation in the Hausdorff Metric, via Relaxation

This work resolves the following question in non-Euclidean statistics: I...
research
10/01/2020

Universal consistency and rates of convergence of multiclass prototype algorithms in metric spaces

We study universal consistency and convergence rates of simple nearest-n...
research
02/21/2023

Contraction and Convergence Rates for Discretized Kinetic Langevin Dynamics

We provide a framework to prove convergence rates for discretizations of...

Please sign up or login with your details

Forgot password? Click here to reset