Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space

Abstract: The first part of this presentation will review connections between problems in the optimal control of diffusion processes, Hamilton-Jacobi-Bellman equations and forward-backward SDEs, having in mind applications in rare event simulation and stochastic filtering. The second part will explain a recent approach based on divergences between probability measures on path space and variational inference that can be used to construct appropriate loss functions in a machine learning framework. This is joint work with Lorenz Richter.

Computer scienceMathematicsPhysics

Audience: researchers in the topic

Data Science and Computational Statistics Seminar