Stochastic Control with Signatures

Jun 3, 2024·
Peter Bank
,
Christian Bayer
,
Paul Peter Hager
,
Sebastian Riedel
Tobias Christian Nauen Tobias Christian Nauen
Abstract
This paper proposes to parameterize open loop controls in stochastic optimal control problems via suitable classes of functionals depending on the driver’s path signature, a concept adopted from rough path integration theory. We rigorously prove that these controls are dense in the class of progressively measurable controls and use rough path methods to establish suitable conditions for stability of the controlled dynamics and target functional. These results pave the way for Monte Carlo methods to stochastic optimal control for generic target functionals and dynamics. We discuss the rather versatile numerical algorithms for computing approximately optimal controls and verify their accurateness in benchmark problems from Mathematical Finance.
Type
Publication
SIAM Journal on Financial Mathematics
publications

This work builds on my master thesis.

For more information, see the full pdf.

Citation

If you use this work, please cite our paper:

@article{Bank2025SignatureControl,
  author = {Bank, Peter and Bayer, Christian and Hager, Paul P. and Riedel,
            Sebastian and Nauen, Tobias},
  title = {Stochastic Control with Signatures},
  journal = {SIAM Journal on Control and Optimization},
  volume = {63},
  number = {5},
  pages = {3189-3218},
  year = {2025},
  doi = {10.1137/24M1667671},
  URL = { https://doi.org/10.1137/24M1667671 },
  eprint = { https://doi.org/10.1137/24M1667671 },
}
Rough Paths Signature Method
Tobias Christian Nauen
Authors
Tobias Christian Nauen
PhD Student
I’m a researcher of artificial intelligence at DFKI and RPTU Kaiserslautern-Landau. My research interests include efficient deep learning, transformer models, multimodal learning, and computer vision. In my PhD project, my focus lies on the development of efficient transformer models for vision, language, and multimodal tasks.