Sampling Using Diffusion Processes, From Langevin to Schrödinger
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore the intricacies of sampling techniques using diffusion processes in this comprehensive lecture by Maxim Raginsky from the University of Illinois at Urbana-Champaign. Delve into the spectrum of methods ranging from Langevin dynamics to Schrödinger's approach, as part of the Geometric Methods in Optimization and Sampling Boot Camp. Over the course of 74 minutes, gain valuable insights into advanced sampling techniques and their applications in optimization and statistical inference.
Syllabus
Sampling Using Diffusion Processes, from Langevin to Schrödinger
Taught by
Simons Institute
Related Courses
Insights on Gradient-Based Algorithms in High-Dimensional LearningSimons Institute via YouTube Estimating Normalizing Constants for Log-Concave Distributions - Algorithms and Lower Bounds
Association for Computing Machinery (ACM) via YouTube Stochastic Analysis and Geometric Functional Inequalities
Hausdorff Center for Mathematics via YouTube Speeding up Langevin Dynamics by Mixing
Society for Industrial and Applied Mathematics via YouTube Optimal Transport and High-Dimensional Probability - Langevin Dynamics via Calculus
Institute for Mathematical Sciences via YouTube