EUVIMEDEUVIMED entdecken
Crossref

A Natural-Gradient Approach for Nonlinear Stochastic Systems with Parameter Uncertainty

Liang Cao

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (22) · 18153-18160

DOI: 10.1609/aaai.v40i22.38877 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Liang Cao.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Controlling nonlinear stochastic systems with parametric uncertainty is a fundamental challenge in modern control theory. This paper presents a comprehensive theoretical framework for a natural-gradient method applied to polynomial chaos theory. We focus on quadratic regulator problems characterized by both parametric uncertainty and additive stochastic disturbances. We extend existing polynomial chaos approaches from linear systems to general nonlinear dynamics. To achieve this, we develop new mathematical tools to handle the complex interactions between nonlinearity, parameter uncertainty, and noise. The framework provides local convergence guarantees for the proposed natural gradient algorithm. Furthermore, it offers practical computational strategies while carefully characterizing the theoretical limitations in the nonlinear setting.

Zitieren

APA

Cao, L. (2026). A Natural-Gradient Approach for Nonlinear Stochastic Systems with Parameter Uncertainty. Proceedings of the AAAI Conference on Artificial Intelligence, 40(22), 18153-18160. https://doi.org/10.1609/aaai.v40i22.38877

Vancouver

Cao L. A Natural-Gradient Approach for Nonlinear Stochastic Systems with Parameter Uncertainty. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(22):18153-18160. doi:10.1609/aaai.v40i22.38877

BibTeX
@article{Cao2026,
  author = {Cao, Liang},
  title = {A Natural-Gradient Approach for Nonlinear Stochastic Systems with Parameter Uncertainty},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {22},
  pages = {18153--18160},
  doi = {10.1609/aaai.v40i22.38877}
}
Kostenlos starten →