A consistent deterministic regression tree for non-parametric prediction of time series - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2014

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

Abstract

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.
Fichier principal
Vignette du fichier
GaillardBaudin2014.pdf (279.88 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00987803 , version 1 (06-05-2014)
hal-00987803 , version 2 (08-05-2014)

Identifiers

Cite

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

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More