Probability and Statistics Seminar——Approximation of heavy-tailed distribution via stable-driven SDEs
报告人： 黄璐静 (福建师大)
地点：Room 1114, Sciences Building No. 1
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. Based on joint work with Mateusz B. Majka and Jian Wang.
About the Speaker:
More Information: https://math.fjnu.edu.cn/6f/32/c15120a290610/page.htm
Your participation is warmly welcomed!