M-Variance Asymptotics and Uniqueness of Descriptors

TL;DR

This paper develops asymptotic theory for the M-variance, the minimum sample loss value, and uses it to test for non-uniqueness of descriptors in various statistical models.

Contribution

It introduces a new asymptotic framework for the M-variance and applies it to hypothesis testing of descriptor uniqueness in complex models.

Findings

M-variance often satisfies a central limit theorem.

The proposed test can detect multiple global minima.

Applications include non-Euclidean means, non-linear regression, and clustering.

Abstract

Asymptotic theory for M-estimation problems usually focuses on the asymptotic convergence of the sample descriptor, defined as the minimizer of the sample loss function. Here, we explore a related question and formulate asymptotic theory for the minimum value of sample loss, the M-variance. Since the loss function value is always a real number, the asymptotic theory for the M-variance is comparatively simple. M-variance often satisfies a standard central limit theorem, even in situations where the asymptotics of the descriptor is more complicated as for example in case of smeariness, or if no asymptotic distribution can be given as can be the case if the descriptor space is a general metric space. We use the asymptotic results for the M-variance to formulate a hypothesis test to systematically determine for a given sample whether the underlying population loss function may have multiple global minima. We discuss three applications of our test to data, each of which presents a typical scenario in which non-uniqueness of descriptors may occur. These model scenarios are the mean on a non-euclidean space, non-linear regression and Gaussian mixture clustering.