RUS  ENG
Full version
SEMINARS

Mathematical Foundations of Artificial Intelligence
October 16, 2024 17:00, Moscow, Steklov Mathematical Institute, Conference hall + Zoom


Nonasymptotic analysis of stochastic approximation algorithms and applications

A. A. Naumovab

a Steklov Mathematical Institute of Russian Academy of Sciences, Moscow
b National Research University Higher School of Economics, Moscow


https://vk.com/video-222947497_456239038
https://youtu.be/fxfMedCHliE


References
  1. A. Durmus, E. Moulines, A. Naumov, S. Samsonov, “Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation”, Mathematics of Operations Research, 2024, 1–30  crossref
  2. S. Samsonov, D. Tiapkin, A. Naumov, E. Moulines, “Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability”, Proceedings of Thirty Seventh Conference on Learning Theory, Proceedings of Machine Learning Research, 247, 2024, 4511–4547 https://proceedings.mlr.press/v247/samsonov24a.html
  3. S. Samsonov, E. Moulines, Qi-Man Shao, Zhuo-Song Zhang, A. Naumov, Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning, NeurIPS, 2023


© Steklov Math. Inst. of RAS, 2024