3 papers
stat.ME2026
Beyond First-order Asymptotics in Sequential Mean Testing
Vikas Deep, Shubhada Agrawal
We revisit the problem of sequentially testing the mean of bounded distributions in a level- power-one framework. We study a -based sequential test that is kn…
math.PR2026
Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise
Shubhada Agrawal, Siva Theja Maguluri, Martin Zubeldia
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 co…
math.ST2024
Markov Chain Variance Estimation: A Stochastic Approximation Approach
Shubhada Agrawal, Prashanth L. A., Siva Theja Maguluri
We consider the problem of estimating the asymptotic variance of a function defined on a Markov chain, an important step for statistical inference of the stationary mean. We design…