Optimal Gaussian concentration bounds for stochastic chains of unbounded memory

TL;DR

This paper establishes optimal Gaussian concentration bounds for stochastic chains with unbounded memory, providing explicit constants and demonstrating their applications in empirical measure fluctuations, Markov approximation, and convergence rates.

Contribution

It introduces the first optimal GCBs for SCUMs under specific conditions, with explicit constants and examples showing the bounds' sharpness.

Findings

Derived a DKW-type inequality for empirical measure fluctuations.

Provided bounds on the $ar{d}$-distance between stationary SCUMs.

Established exponential convergence rates for Birkhoff sums.

Abstract

We obtain optimal Gaussian concentration bounds (GCBs) for stochastic chains of unbounded memory (SCUMs) on countable alphabets. These stochastic processes are also known as "chains with complete connections" or "$g$-measures". We consider two different conditions on the kernel: (1) when the sum of its oscillations is less than one, or (2) when the sum of its variations is finite, i.e., belongs to $\ell^1(\mathbb{N})$. We also obtain explicit constants as functions of the parameters of the model. The proof is based on maximal coupling. Our conditions are optimal in the sense that we exhibit examples of SCUMs that do not have GCB and for which the sum of oscillations is strictly larger than one, or the variation belongs to $\ell^{1+\epsilon}(\mathbb{N})$ for any $\epsilon > 0$. These examples are based on the existence of phase transitions. We also extend the validity of GCB to a class of functions which can depend on infinitely many coordinates. We illustrate our results by three applications. First, we derive a Dvoretzky-Kiefer-Wolfowitz type inequality which gives a uniform control on the fluctuations of the empirical measure. Second, in the finite-alphabet case, we obtain an upper bound on the $\bar{d}$-distance between two stationary SCUMs and, as a by-product, we obtain new (explicit) bounds on the speed of Markovian approximation in $\bar{d}$. Third, we obtain exponential rate of convergence for Birkhoff sums of a certain class of observables.