Build AI Apps with Azure, Copilot, and Generative AI — Microsoft Certified
Master Windows Internals - Kernel Programming, Debugging & Architecture
Overview
AI, Data Science & Cloud Certificates from Google, IBM & Meta — 40% Off
One plan covers every Professional Certificate on Coursera. 40% off Coursera Plus Annual.
Unlock All Certificates
Watch a 48-minute lecture by Tyler Maunu from Brandeis University titled "Subspace Langevin Monte Carlo" presented at IPAM's Statistical and Numerical Methods for Non-commutative Optimal Transport Workshop on May 21, 2025. Explore this novel and efficient sampling method that generalizes coordinate and preconditioned Langevin Monte Carlo to address the computational challenges of sampling from high-dimensional distributions. Understand how this method extends subspace descent techniques from Euclidean space to Wasserstein space, with additional discussion on subspace Wasserstein descent in other settings if time permits. For more information about this workshop hosted by the Institute for Pure & Applied Mathematics (IPAM), visit their website.
Syllabus
Tyler Maunu - Subspace Langevin Monte Carlo - IPAM at UC:A
Taught by
Institute for Pure & Applied Mathematics (IPAM)