Seminar Event Detail


Financial/Actuarial Mathematics

Date:  Wednesday, February 16, 2022
Location:  Zoom Virtual (4:00 PM to 5:00 PM)

Title:  Convergence of Deep Solvers for Semilinear PDEs

Abstract:   We derive convergence rates for a deep learning algorithm for semilinear partial differential equations which is based on a Feynman-Kac representation in terms of an uncoupled forward-backward stochastic differential equation and a discretization in time of the stochastic equation. We show that the error of the deep learning algorithm is bounded in terms of its loss functional, hence yielding a direct measure to judge the quality of the deep solver in numerical applications, and that the loss functional converges sufficiently fast to zero to guarantee that the error of the deep learning algorithm vanishes in the limit. As a consequence of these results, we argue that the deep solver has a strong convergence rate of order 1/2. The talk is based on joint work with Oliver Hager, Lotte Schnell, Charlotte Reimers (TU Berlin) and Maximilian W├╝rschmidt (Trier University).

Files: 7642_Belak.pdf


Speaker:  Christoph Belak
Institution:  TU Berlin

Event Organizer:     

 

Edit this event (login required).
Add new event (login required).
For access requests and instructions, contact math-webmaster@umich.edu

Back to previous page
Back to UM Math seminars/events page.