Deep BSDE Solver on Bounded Domains Part I: General Loss Rate
Probability
2025-08-21 v1 Numerical Analysis
Numerical Analysis
Abstract
We consider a ramification of the deep BSDE loss functional designed to apply for BSDEs on bounded domains, i.e. with random (unbounded) time horizons. We derive a general convergence rate of the loss functional; precisely for a class of (randomly) weighted modifications of the functional. The rate is expressed in terms of the underlying discrete-time stepsize and a universal approximation distance.
Keywords
Cite
@article{arxiv.2508.14215,
title = {Deep BSDE Solver on Bounded Domains Part I: General Loss Rate},
author = {Maximilian Würschmidt},
journal= {arXiv preprint arXiv:2508.14215},
year = {2025}
}
Comments
26 pages