YoVDO

An Exploration-Agnostic Characterization of the Ergodicity of Parallel Tempering

Offered By: Centre de recherches mathématiques - CRM via YouTube

Tags

Markov Chain Monte Carlo Courses Bayesian Statistics Courses Ergodicity Courses Kullback-Leibler Divergence Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the ergodicity of parallel tempering in this 48-minute lecture from the Colloque des sciences mathématiques du Québec. Delve into Trevor Campbell's research on non-reversible parallel tempering (NRPT) and its effectiveness in sampling from complex target distributions. Examine the uniform geometric ergodicity of NRPT under an efficient local exploration hypothesis and understand how the global communication barrier (GCB) plays a role in bounding ergodicity rates. Compare NRPT with classical reversible parallel tempering and gain insights into their relative performance. Investigate the properties of GCB and its relationships with total variation distance and Kullback-Leibler divergences. Conclude by reviewing simulations that validate the theoretical analysis presented, based on collaborative work with Nikola Surjanovic, Saifuddin Syed, and Alexandre Bouchard-Côté.

Syllabus

Trevor Campbell: An exploration-agnostic characterization of the ergodicity of parallel tempering


Taught by

Centre de recherches mathématiques - CRM

Related Courses

Probabilistic Graphical Models 2: Inference
Stanford University via Coursera
Probabilistic Machine Learning
Eberhard Karls University of Tübingen via YouTube
Mathematical understanding of uncertainty
Seoul National University via edX
Bayesian Statistics - A Comprehensive Course
Ox educ via YouTube
Sampling Crash Course
Simons Institute via YouTube