AI RESEARCH
Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains
arXiv CS.LG
•
ArXi:2601.08184v3 Announce Type: replace-cross Non-asymptotic central limit theorem (CLT) rates play a central role in modern machine learning and operations research. In this paper, we study CLT rates for multivariate dependent data in Wasserstein-$p$ ($W_p$) distance, for general $p\ge 1$. We focus on two fundamental dependence structures that commonly arise in practice: locally dependent sequences and geometrically ergodic Marko chains.