Showing 2026Show all
3 papers · 1 filter
cs.LG2026
A Concentration Bound for Two-Timescale Actor-Critic Algorithm
Prashansa Panda, Shalabh Bhatnagar
Significant research effort has been directed in recent years towards establishing both asymptotic and non-asymptotic convergence guarantees for two-timescale actor--critic algorit…
math.OC2026
Stochastic Mirror Descent under Iterate-Dependent Markov Noise: Analysis in the Asymptotic and Finite Time Regimes
Anik Kumar Paul, Shalabh Bhatnagar
We study a stochastic optimization problem in which the sampling distribution depends on the decision variable, and the available samples are generated through an iterate-dependent…
cs.LG2026
Finite-time analysis of Multi-timescale Stochastic Optimization Algorithms
Kaustubh Kartikey, Shalabh Bhatnagar
We present a finite-time analysis of two smoothed functional stochastic approximation algorithms for simulation-based optimization. The first is a two time-scale gradient-based met…