Deep Learning based algorithm for nonlinear PDEs in finance and gradient descent type algorithm for non-convex stochastic optimization problems with ReLU neural networks

Dr. Ariel Neufeld, Nanyang Technological University (NTU)

Wednesday, 18th October 2023

Abstract:


In this talk, we first present a deep-learning based algorithm which can solve nonlinear parabolic PDEs in up to 10’000 dimensions with short run times, and apply it to price high-dimensional financial derivatives under default risk.
Then, we discuss a general problem when training neural networks, namely that it typically involves non-convex stochastic optimization.
To that end, we present TUSLA,  a gradient descent type algorithm (or more precisely : stochastic gradient Langevin dynamics algorithm) for which we can prove that it can solve non-convex stochastic optimization problems involving ReLU neural networks.
This talk is based on joint works with C. Beck, S. Becker, P. Cheridito, A. Jentzen, and  D.-Y. Lim, S. Sabanis, Y. Zhang, respectively.

 

 

 

 

 

Back to: Institute for Financial and Actuarial Mathematics