Statistical Applications of Wasserstein Gradient Flows
Offered By: Paul G. Allen School via YouTube
Course Description
Overview
Explore a distinguished seminar on statistical applications of Wasserstein gradient flows presented by Professor Philippe Rigollet from MIT. Delve into the fundamental concepts of Otto calculus in mathematical optimal transport, understanding how it imparts Riemannian structure to the Wasserstein space of probability measures. Learn about computing Riemannian gradients of functionals over this space and optimizing them using Wasserstein gradient flows. Discover the practical applications of these concepts in statistical fields such as variational inference and maximum likelihood estimation for Gaussian mixture models. Gain insights from Rigollet's expertise at the intersection of statistics, machine learning, and optimization, with a focus on high-dimensional problems and recent research in statistical optimal transport for geometric data analysis and sampling.
Syllabus
Distinguished Seminar in Optimization and Data: Philippe Rigollet (MIT)
Taught by
Paul G. Allen School
Related Courses
K-Means and K-Medians Under Dimension ReductionSimons Institute via YouTube Can Non-Convex Optimization Be Robust?
Simons Institute via YouTube Robust Estimation and Generative Adversarial Nets
Simons Institute via YouTube Invariance, Causality and Novel Robustness
Simons Institute via YouTube The Importance of Better Models in Stochastic Optimization
Simons Institute via YouTube