Empirical PAC-Bayes Bounds for Markov Chains

Vahe Karagulyan, Pierre Alquier

TL;DR: Fully empirical PAC-Bayes bounds when the observations are not i.i.d. but time time dependent: Markov chain.

Abstract: The core of generalization theory was developed for independent observations. Some PAC and PAC-Bayes bounds are available for data that exhibit a temporal dependence. However, there are constants in these bounds that depend on properties of the data-generating process: mixing coefficients, mixing time, spectral gap... Such constants are unknown in practice. In this paper, we prove a new PAC-Bayes bound for Markov chains. This bound depends on a quantity called the \textit{pseudo-spectral gap}, $\gamma_{ps}$. The main novelty is that we can provide an empirical bound on $\gamma_{ps}$ when the state space is finite. Thus, we obtain the first fully empirical PAC-Bayes bound for Markov chains. This extends beyond the finite case, although this requires additional assumptions. On simulated experiments, the empirical version of the bound is essentially as tight as the one that depends on $\gamma_{ps}$.

Code Dataset Url: https://github.com/v-ahe/empirical-pac-bayes-markov/tree/main

Submission Number: 186