Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains

arXiv:2601.08184v3 Announce Type: replace-cross Abstract: 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 pge 1. We focus on two fundamental dependence structures that commonly arise in practice: locally dependent sequences and geometrically ergodic Markov chains. In both settings, we establish the first optimal mathcal O(n^{-1/2}) rate in W_1, as well as the first W_p (pge 2) CLT rates under mild moment assumptions, substantially improving the best previously known bounds in these dependent-data regimes. As an application of our optimal W_1 rate for locally dependent sequences, we further obtain the first optimal W_1-CLT rate for multivariate U-statistics. On the technical side, we derive a tractable auxiliary bound for W_1 Gaussian approximation errors that is well suited for studying dependent data. For Markov chains, we further prove that the regeneration time of the split chain associated with a geometrically ergodic chain has a geometric tail without assuming strong aperiodicity or other restrictive conditions. These tools may be of independent interests and enable our optimal W_1 rates and underpin our W_p (pge 2) results.

Related

• Gaussian Approximation for Asynchronous Q-learning
• Central Limit Theorems for Asynchronous Averaged Q-Learning
• Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space

Source: arXiv cs.LG | 2026-04-21