AI RESEARCH

Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise

arXiv CS.LG

ArXi:2605.20999v1 Announce Type: cross We establish maximal concentration bounds for the iterates generated by stochastic approximation algorithms with general step sizes, where the noise has a finite-state Markovian component plus a Martingale-difference component.