A Short Information-Theoretic Analysis of Linear Auto-Regressive Learning
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916387918708736 |
|---|---|
| author | Ziemann, Ingvar |
| author_facet | Ziemann, Ingvar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_06437 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Short Information-Theoretic Analysis of Linear Auto-Regressive Learning Ziemann, Ingvar Machine Learning Systems and Control 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. |
| title | A Short Information-Theoretic Analysis of Linear Auto-Regressive Learning |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2409.06437 |