English

A high dimensional Central Limit Theorem for martingales, with applications to context tree models

Statistics Theory 2018-09-11 v1 Probability Statistics Theory

Abstract

We establish a central limit theorem for (a sequence of) multivariate martingales which dimension potentially grows with the length nn of the martingale. A consequence of the results are Gaussian couplings and a multiplier bootstrap for the maximum of a multivariate martingale whose dimensionality dd can be as large as ence^{n^c} for some c>0c>0. We also develop new anti-concentration bounds for the maximum component of a high-dimensional Gaussian vector, which we believe is of independent interest. The results are applicable to a variety of settings. We fully develop its use to the estimation of context tree models (or variable length Markov chains) for discrete stationary time series. Specifically, we provide a bootstrap-based rule to tune several regularization parameters in a theoretically valid Lepski-type method. Such bootstrap-based approach accounts for the correlation structure and leads to potentially smaller penalty choices, which in turn improve the estimation of the transition probabilities.

Keywords

Cite

@article{arxiv.1809.02741,
  title  = {A high dimensional Central Limit Theorem for martingales, with applications to context tree models},
  author = {Alexandre Belloni and Roberto I. Oliveira},
  journal= {arXiv preprint arXiv:1809.02741},
  year   = {2018}
}
R2 v1 2026-06-23T03:58:42.309Z