skip to main content
Caltech

CMX Lunch Seminar

Wednesday, April 24, 2024
12:00pm to 1:00pm
Add to Cal
Annenberg 213
Enhancing PDE Computations and Score-Based Generative Models through Optimization
Siting Liu, Adjunct Assistant Professor of Mathematics, Department of Mathematics, University of California Los Angeles,

This presentation explores optimization strategies for improving both partial differential equation (PDE) computations and score-based generative models (SGM). In the realm of numerical computations, we introduce a saddle point framework that capitalizes on the inherent structure of PDEs. Integrated seamlessly with existing discretization schemes, this framework eliminates the necessity for nonlinear inversions, paving the way for efficient parallelization. Shifting focus to SGM, we delve into the Wasserstein proximal operator (WPO) to understand the mathematical foundations of SGM - it can be written as the Wasserstein proximal operators of cross-entropy. Leveraging PDE formulation of WPO, we propose an WPO-informed score model which showcases accelerated training and reduced data requirements.

For more information, please contact Jolene Brink by phone at (626)395-2813 or by email at [email protected] or visit CMX Website.