EUVIMEDEUVIMED entdecken
Crossref

Convergence of Over-the-Air Federated Learning With Imperfect Channel Estimates: A Unified View

Sayantan Adhikary, Neelesh B. Mehta

IEEE Transactions on Wireless Communications · 2026 · 25 · 19533-19547

DOI: 10.1109/twc.2026.3708141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Sayantan Adhikary und 1 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Gefördert von: Qualcomm 6G University Research (UR) Program and in part by the J. C. Bose Fellowship.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Over-the-air computation-assisted federated learning (OTA-FL) exploits the superposition property of the wireless channel to markedly reduce the latency and bandwidth requirements of federated learning. Devices adapt their transmit power to enable over-the-air aggregation of the local models. However, imperfect channel state information (CSI) and power constraints distort the aggregated model update at the receiver and affect the learning algorithm. We provide a novel, comprehensive analysis of OTA-FL schemes, which encompasses scaled-down channel inversion (SCI), truncated channel inversion (TCI), and controlled descent algorithm (CDA). Unlike prior studies that assume bounded estimation errors, we study a more realistic model in which the estimation error has unbounded support. Our analysis addresses both fixed and adaptive learning rates. While prior works on imperfect CSI focus only on convergence in expectation for a specific scheme and assume fixed learning rates, we provide technically stronger almost sure convergence guarantees for multiple schemes when the number of devices is large. Extensive experiments on linear regression and CIFAR-10 classification validate our theory even for a small number of devices. Adapting the learning rate leads to convergence even with very noisy estimates.

Förderung

  • Qualcomm 6G University Research (UR) Program and in part by the J. C. Bose Fellowship

Zitieren

APA

Adhikary, S., & Mehta, N. B. (2026). Convergence of Over-the-Air Federated Learning With Imperfect Channel Estimates: A Unified View. IEEE Transactions on Wireless Communications, 25, 19533-19547. https://doi.org/10.1109/twc.2026.3708141

Vancouver

Adhikary S, Mehta NB. Convergence of Over-the-Air Federated Learning With Imperfect Channel Estimates: A Unified View. IEEE Transactions on Wireless Communications. 2026;25:19533-19547. doi:10.1109/twc.2026.3708141

BibTeX
@article{Adhikary2026,
  author = {Adhikary, Sayantan and Mehta, Neelesh B.},
  title = {Convergence of Over-the-Air Federated Learning With Imperfect Channel Estimates: A Unified View},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2026},
  volume = {25},
  pages = {19533--19547},
  doi = {10.1109/twc.2026.3708141}
}
Kostenlos starten →