Identifiability for mixtures of centered Gaussians and sums of powers of quadratics

TL;DR

This paper investigates the identifiability of mixtures of centered Gaussian distributions through their moments, establishing conditions under which the mixture components can be uniquely recovered for degrees up to six.

Contribution

It proves generic identifiability of Gaussian mixtures from moments of degree up to six, using geometric and secant variety techniques, extending to sums of powers of forms.

Findings

Identifiability holds for mixtures with up to a certain number of components.

The results apply to moments of degree up to six.

The methods extend to sums of powers of forms for higher degrees.

Abstract

We consider the inverse problem for the polynomial map which sends an $m$-tuple of quadratic forms in $n$ variables to the sum of their $d$-th powers. This map captures the moment problem for mixtures of $m$ centered $n$-variate Gaussians. In the first non-trivial case $d = 3$, we show that for any $ n\in \mathbb N $, this map is generically one-to-one (up to permutations of $ q_1,\ldots, q_m $ and third roots of unity) in two ranges: $m\le {n\choose 2} + 1 $ for $n \leq 16$ and $ m\le {n+5 \choose 6}/{n+1 \choose 2}-{n+1 \choose 2}-1$ for $n > 16$, thus proving generic identifiability for mixtures of centered Gaussians from their (exact) moments of degree at most $ 6 $. The first result is obtained by studying the explicit geometry of the tangential contact locus of the variety of sums of cubes of quadratic forms at concrete points, while the second result is accomplished using a link between secant non-defectivity with identifiability. The latter approach generalizes also to sums of $ d $-th powers of $k$-forms for $d \geq 3$ and $k \geq 2$.