Approximation of heavy-tailed distributions via stable-driven SDEs

TL;DR

This paper develops a theoretical framework for approximating heavy-tailed distributions using ergodic SDEs driven by symmetric alpha-stable processes, addressing limitations of traditional Brownian-motion-based methods.

Contribution

It introduces a rigorous approach to using stable-driven SDEs for sampling heavy-tailed distributions, expanding the tools beyond Brownian motion-based SDEs.

Findings

Provides a theoretical foundation for stable-driven SDEs in sampling

Shows potential for improved sampling of heavy-tailed distributions

Addresses ergodicity issues in traditional methods

Abstract

Constructions of numerous approximate sampling algorithms are based on the well-known fact that certain Gibbs measures are stationary distributions of ergodic stochastic differential equations (SDEs) driven by the Brownian motion. However, for some heavy-tailed distributions it can be shown that the associated SDE is not exponentially ergodic and that related sampling algorithms may perform poorly. A natural idea that has recently been explored in the machine learning literature in this context is to make use of stochastic processes with heavy tails instead of the Brownian motion. In this paper we provide a rigorous theoretical framework for studying the problem of approximating heavy-tailed distributions via ergodic SDEs driven by symmetric (rotationally invariant) $\alpha$-stable processes.