Concentration bounds for two time scale stochastic approximation

2018/06/28 by Borkar, Vivek S., Pattathil, Sarath
#FOS: Mathematics #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.1806.10798

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.

Related

• Concentration Bounds for Stochastic Approximations
• Functional Central Limit Theorem for Two Timescale Stochastic Approximation
• A Concentration Bound for Distributed Stochastic Approximation
• A Concentration Bound for Stochastic Approximation via Alekseev's\n Formula
• Stochastic Approximation with Two Time Scales: The General Case