Convergence rates of Gibbs measures with degenerate minimum

Abstract

We study convergence rates for Gibbs measures, with density proportional to $e^{-f(x)/t}$, as $t\to 0$ where $f:{\mathbb{R}}^d\to \mathbb{R}$ admits a unique global minimum at $x^{\star }$. We focus on the case where the Hessian is not definite at $x^{\star }$. We assume instead that the minimum is strictly polynomial and give a higher order nested expansion of $f$ at $x^{\star }$, which depends on every coordinate. We give an algorithm yielding such a decomposition if the polynomial order of $x^{\star }$ is no more than $8$, in connection with Hilbert's $17^{\text{th}}$ problem. However, we prove that the case where the order is $10$ or higher is fundamentally different and that further assumptions are needed. We then give the rate of convergence of Gibbs measures using this expansion. Finally we adapt our results to the multiple well case.

arXiv comment25 pages

References in corpus (4)

• Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
• Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
• Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond
• Theoretical guarantees for approximate sampling from smooth and log-concave densities

Cited by in corpus (1)

• Swing contract pricing: with and without Neural Networks