A Short Information-Theoretic Analysis of Linear Auto-Regressive Learning
Machine Learning
2024-09-11 v1 Systems and Control
Systems and Control
Machine Learning
Abstract
In this note, we give a short information-theoretic proof of the consistency of the Gaussian maximum likelihood estimator in linear auto-regressive models. Our proof yields nearly optimal non-asymptotic rates for parameter recovery and works without any invocation of stability in the case of finite hypothesis classes.
Cite
@article{arxiv.2409.06437,
title = {A Short Information-Theoretic Analysis of Linear Auto-Regressive Learning},
author = {Ingvar Ziemann},
journal= {arXiv preprint arXiv:2409.06437},
year = {2024}
}