General oracle inequalities for a penalized log-likelihood criterion based on non-stationary data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aubert, Julien, Lehéricy, Luc, Reynaud-Bouret, Patricia
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909205890334720
author Aubert, Julien
Lehéricy, Luc
Reynaud-Bouret, Patricia
author_facet Aubert, Julien
Lehéricy, Luc
Reynaud-Bouret, Patricia
contents We prove oracle inequalities for a penalized log-likelihood criterion that hold even if the data are not independent and not stationary, based on a martingale approach. The assumptions are checked for various contexts: density estimation with independent and identically distributed (i.i.d) data, hidden Markov models, spiking neural networks, adversarial bandits. In each case, we compare our results to the literature, showing that, although we lose some logarithmic factors in the most classical case (i.i.d.), these results are comparable or more general than the existing results in the more dependent cases.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10582
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle General oracle inequalities for a penalized log-likelihood criterion based on non-stationary data
Aubert, Julien
Lehéricy, Luc
Reynaud-Bouret, Patricia
Statistics Theory
We prove oracle inequalities for a penalized log-likelihood criterion that hold even if the data are not independent and not stationary, based on a martingale approach. The assumptions are checked for various contexts: density estimation with independent and identically distributed (i.i.d) data, hidden Markov models, spiking neural networks, adversarial bandits. In each case, we compare our results to the literature, showing that, although we lose some logarithmic factors in the most classical case (i.i.d.), these results are comparable or more general than the existing results in the more dependent cases.
title General oracle inequalities for a penalized log-likelihood criterion based on non-stationary data
topic Statistics Theory
url https://arxiv.org/abs/2405.10582