The PIMS Postdoctoral Fellow Seminar: Shirou Wang (Online)

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.

This event is part of the Emergent Research: The PIMS Postdoctoral Fellow Colloquium Series. To learn about other events in this series and to receive connection details, please register for the event mailing list.

This event took place via zoom and a recording is available on mathtube.org.