EUVIMEDEUVIMED entdecken
Crossref

Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications

Yue Huang, Zhaoxian Wu, Shiqian Ma, Qing Ling

IEEE Transactions on Signal Processing · 2025 · 73 · 1939-1953

DOI: 10.1109/tsp.2025.3569665 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Signal Processing, 2025. Verfasst von Yue Huang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: NSF China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Stochastic approximation (SA) that involves multiple coupled sequences, also known as multiple-sequence SA (MSSA), finds diverse applications in the fields of signal processing and machine learning. However, existing theoretical understandings of MSSA are limited: the multi-timescale analysis implies a slow convergence rate, whereas the single-timescale analysis relies on a stringent fixed point smoothness assumption. In this paper, we establish tighter single-timescale analysis for MSSA, without assuming smoothness of the fixed points. Our theoretical findings reveal that, when all involved operators are strongly monotone, MSSA converges at a rate of $\tilde{\mathcal{O}}(K^{-1})$ , where $K$ denotes the total number of iterations. When all involved operators are strongly monotone except for the main one, MSSA converges at a rate of $O(K^{-\frac{1}{2}})$ . These rates align with the ones established for single-sequence SA. Applying our novel theoretical findings to bilevel optimization and communication-efficient distributed learning offers relaxed assumptions and/or simpler algorithms with perfor- mance guarantees, as validated by numerical experiments.

Förderung

  • NSF China

Zitieren

APA

Huang, Y., Wu, Z., Ma, S., & Ling, Q. (2025). Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications. IEEE Transactions on Signal Processing, 73, 1939-1953. https://doi.org/10.1109/tsp.2025.3569665

Vancouver

Huang Y, Wu Z, Ma S, Ling Q. Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications. IEEE Transactions on Signal Processing. 2025;73:1939-1953. doi:10.1109/tsp.2025.3569665

BibTeX
@article{Huang2025,
  author = {Huang, Yue and Wu, Zhaoxian and Ma, Shiqian and Ling, Qing},
  title = {Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications},
  journal = {IEEE Transactions on Signal Processing},
  year = {2025},
  volume = {73},
  pages = {1939--1953},
  doi = {10.1109/tsp.2025.3569665}
}
Kostenlos starten →