A coupling approach in the computation of geometric ergodicity for stochastic dynamics
Date: Wed, Dec 16, 2020
Location: Zoom, PIMS,University of Alberta
Conference: Emergent Research: The PIMS Postdoctoral Fellow Seminar
Subject: Mathematics
Class: Scientific
Abstract:
This talk introduces a probabilistic approach to numerically compute geometric convergence rates in discrete or continuous stochastic systems. Choosing appropriate coupling mechanisms and combining them together, works well in many settings, especially in high-dimensions. Using this approach, it is observed that the rate of geometric ergodicity of a randomly perturbed system can, to some extent, reveal the degree of chaoticity of the unperturbed system. Potential applications of the coupling method and the visualization of higher dimensional non-convex functions, e.g., the loss functions of neural networks, will be discussed.