Monte Carlo Seminar| Sinho Chewi| A local error framework in KL divergence via shifted composition
Автор: Monte Carlo Seminar
Загружено: 2025-03-18
Просмотров: 238
Organized by Online Monte Carlo Seminar
[sites.google.com/view/monte-carlo-seminar]
Speaker: Sinho Chewi (Yale University)
Title: A local error framework in KL divergence via shifted composition
Abstract: Local error analysis is a standard framework for establishing error estimates for the numerical discretization of stochastic systems. However, it is traditionally limited to guarantees in the Wasserstein metric. In this talk, I will describe a strengthening of this framework which yields bounds in the stronger sense of KL divergence or relative entropy. At the heart of this result is a technique to use coupling arguments to control information-theoretic divergences. This technique, which we call "shifted composition", builds on a recent line of work developed with my co-author Jason M. Altschuler.
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
