?
SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
Ch. 37. P. 13927–13981.
Ключевые слова: linear stochastic approximationстохастическая аппроксимацияTD LearningTaming Heterogeneity
ПУБЛИКАЦИЯ ПОДГОТОВЛЕНА ПО РЕЗУЛЬТАТАМ ПРОЕКТА:
Левин И. В., Наумов А. А., Самсонов С. В., , in: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-26: AAAI Technical Track on Planning, Routing, and Scheduling; AAAI Technical Track on Reasoning under Uncertainty; AAAI Technical Track on Search and Optimization. Main Track, volume 40 no. 43.: American Association for Artificial Intelligence (AAAI) Press, 2026. P. 36696–36704.
Добавлено: 17 апреля 2026 г.
Самсонов С. В., Шешукова М. Е., Moulines E. и др., , in: 39th Conference on Neural Information Processing Systems (NeurIPS 2025).: NeurIPS, 2025. P. 174565–174626.
Добавлено: 26 января 2026 г.
Самсонов С. В., Тяпкин Д. Н., Наумов А. А. и др., , in: Proceedings of Machine Learning Research. Volume 247: The Thirty Seventh Annual Conference on Learning Theory, 30-3 July 2023, Edmonton, Canada.: PMLR, 2024. Ch. 247 P. 4511–4547.
Добавлено: 13 октября 2024 г.
Durmus A., Мулине Э. Ф., Наумов А. А. и др., Mathematics of Operations Research 2025 Vol. 50 No. 2 P. 935–964
Добавлено: 13 июля 2022 г.
Durmus A., Мулине Э. Ф., Наумов А. А. и др., , in: Advances in Neural Information Processing Systems 34 (NeurIPS 2021).: Curran Associates, Inc., 2021. P. 30063–30074.
This paper provides a non-asymptotic analysis of linear stochastic approximation (LSA) algorithms with fixed stepsize. This family of methods arises in many machine learning tasks and is used to obtain approximate solutions of a linear system $\bar{A}\theta = \bar{b}$ for which $\bar{A}$ and $\bar{b}$ can only be accessed through random estimates $\{({\bf A}_n, {\bf b}_n): ...
Добавлено: 17 февраля 2022 г.
Durmus A., Мулине Э. Ф., Наумов А. А. и др., , in: Proceedings of Machine Learning ResearchVol. 134: Conference on Learning Theory.: PMLR, 2021. P. 1711–1752.
Добавлено: 6 августа 2021 г.