Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning

Author name not available (Why is that?)

Publication date: 21 June 2022

Abstract: The combination of Monte Carlo methods and deep learning has recently led to efficient algorithms for solving partial differential equations (PDEs) in high dimensions. Related learning problems are often stated as variational formulations based on associated stochastic differential equations (SDEs), which allow the minimization of corresponding losses using gradient-based optimization methods. In respective numerical implementations it is therefore crucial to rely on adequate gradient estimators that exhibit low variance in order to reach convergence accurately and swiftly. In this article, we rigorously investigate corresponding numerical aspects that appear in the context of linear Kolmogorov PDEs. In particular, we systematically compare existing deep learning approaches and provide theoretical explanations for their performances. Subsequently, we suggest novel methods that can be shown to be more robust both theoretically and numerically, leading to substantial performance improvements.

Has companion code repository: https://github.com/juliusberner/robust_kolmogorov

This page was built for publication: Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6402779)