A consistent deterministic regression tree for non-parametric prediction of time series

Pierre Gaillard (1, 2) , Paul Baudin (3)

1 EDF R&D - EDF R&D
2 GREGH - Groupement de Recherche et d'Etudes en Gestion à HEC
3 Clime - Coupling environmental data and simulation models for software integration

We study online prediction of bounded stationary ergodic processes. To do so, we consider the setting of prediction of individual sequences and build a deterministic regression tree that performs asymptotically as well as the best L-Lipschitz constant predictors. Then, we show why the obtained regret bound entails the asymptotical optimality with respect to the class of bounded stationary ergodic processes.

Domaines: Statistiques [math.ST]; Machine Learning [stat.ML]; Apprentissage [cs.LG]; Théorie [stat.TH]

Pierre Gaillard, Paul Baudin. A consistent deterministic regression tree for non-parametric prediction of time series. 2014. ⟨hal-00987803v2⟩