2025
Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way
AISTATS 2025poster
Previous studies on two-timescale stochastic approximation (SA) mainly focused on bounding mean-squared errors under diminishing stepsize schemes. In this work, we investigate {\it constant} stpesize schemes through the lens of Markov processes, proving that the iterates of both timescales converge…