Concentration bounds for two time scale stochastic approximation
Optimization and Control
2018-06-29 v1
Abstract
Viewing a two time scale stochastic approximation scheme as a noisy discretization of a singularly perturbed differential equation, we obtain a concentration bound for its iterates that captures its behavior with quantifiable high probability. This uses Alekseev's nonlinear variation of constants formula and a martingale concentration inequality and extends the corresponding results for single time scale stochastic approximation.
Cite
@article{arxiv.1806.10798,
title = {Concentration bounds for two time scale stochastic approximation},
author = {Vivek S. Borkar and Sarath Pattathil},
journal= {arXiv preprint arXiv:1806.10798},
year = {2018}
}
Comments
8 pages