Approximation of heavy-tailed distributions via stable-driven SDEs

Lu-Jing Huang, Mateusz B. Majka, Jian Wang

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)
49 Downloads (Pure)


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) α-stable processes.
Original languageEnglish
Pages (from-to)2040-2068
Number of pages29
Issue number3
Early online date10 May 2021
Publication statusPublished - Aug 2021


  • Approximate sampling
  • Fractional langevin monte carlo
  • Heavy-tailed distributions
  • Invariant measures
  • Stochastic differential equations
  • Symmetric a-stable processes

ASJC Scopus subject areas

  • Statistics and Probability


Dive into the research topics of 'Approximation of heavy-tailed distributions via stable-driven SDEs'. Together they form a unique fingerprint.

Cite this