# Exponential inequalities for nonstationary Markov chains

Exponential inequalities are main tools in machine learning theory. To prove exponential inequalities for non i.i.d random variables allows to extend many learning techniques to these variables. Indeed, much work has been done both on inequalities and learning theory for time series, in the past 15 years. How-ever, for the non-independent case, almost all the results concern stationary time series. This excludes many important applications: for example any series with a periodic behaviour is nonstationary. In this paper, we extend the basic tools of [19] to nonstationary Markov chains. As an application, we provide a Bernstein-type inequality, and we deduce risk bounds for the prediction of periodic autoregressive processes with an unknown period Lien vers l'article

ALQUIER, P., DOUKHAN, P. and FAN, X. (2019). Exponential inequalities for nonstationary Markov chains. *Dependence Modeling*, 7(1), pp. 150-168.

Mots clés : #Nonstationary-Markov-chains, #Martingales, #Exponential-inequalities, #Time-series-forecasting, #Sta, #tistical-learning-theory, #Oracle-inequalities, #Model-selection