EUVIMEDEUVIMED entdecken
Crossref

A Uniform Framework of Yau–Yau Algorithm Based on Deep Learning With the Capability of Overcoming the Curse of Dimensionality

Xiuqiong Chen, Zeju Sun, Yangtianze Tao, Stephen S.-T. Yau

IEEE Transactions on Automatic Control · 2025-01 · 70 (1) · 339-354

DOI: 10.1109/tac.2024.3424628 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Automatic Control, 2025-01. Verfasst von Xiuqiong Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Tsinghua University Education Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In numerous application areas, high-dimensional nonlinear filtering is still a challenging problem. The introduction of deep learning and neural networks has improved the efficiency of classical algorithms and they perform well in many practical tasks. However, a theoretical interpretation of their feasibility is still lacking. In this article, we exploit the representational ability of recurrent neural networks (RNNs) and provide a computationally efficient and optimal framework for nonlinear filter design based on the Yau–Yau algorithm and RNNs. Theoretically, it can be proved that the size of the neural network required in this algorithm increases only polynomially rather than exponentially with dimension, which implies that the Yau–Yau algorithm based on RNNs has the ability to overcome the curse of dimensionality. Numerical results also show that our method is more competitive than classical algorithms for high-dimensional problems.

Förderung

  • National Natural Science Foundation of China
  • Tsinghua University Education Foundation

Zitieren

APA

Chen, X., Sun, Z., Tao, Y., & Yau, S. S. (2025). A Uniform Framework of Yau–Yau Algorithm Based on Deep Learning With the Capability of Overcoming the Curse of Dimensionality. IEEE Transactions on Automatic Control, 70(1), 339-354. https://doi.org/10.1109/tac.2024.3424628

Vancouver

Chen X, Sun Z, Tao Y, Yau SS. A Uniform Framework of Yau–Yau Algorithm Based on Deep Learning With the Capability of Overcoming the Curse of Dimensionality. IEEE Transactions on Automatic Control. 2025;70(1):339-354. doi:10.1109/tac.2024.3424628

BibTeX
@article{Chen2025,
  author = {Chen, Xiuqiong and Sun, Zeju and Tao, Yangtianze and Yau, Stephen S.-T.},
  title = {A Uniform Framework of Yau–Yau Algorithm Based on Deep Learning With the Capability of Overcoming the Curse of Dimensionality},
  journal = {IEEE Transactions on Automatic Control},
  year = {2025},
  volume = {70},
  number = {1},
  pages = {339--354},
  doi = {10.1109/tac.2024.3424628}
}
Kostenlos starten →