A variational Bayes approach to debiased inference for low-dimensional parameters in high-dimensional linear regression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915438501298176 |
|---|---|
| author | Castillo, Ismaël L'Huillier, Alice Ray, Kolyan Travis, Luke |
| author_facet | Castillo, Ismaël L'Huillier, Alice Ray, Kolyan Travis, Luke |
| contents | We propose a scalable variational Bayes method for statistical inference for a single or low-dimensional subset of the coordinates of a high-dimensional parameter in sparse linear regression. Our approach relies on assigning a mean-field approximation to the nuisance coordinates and carefully modelling the conditional distribution of the target given the nuisance. This requires only a preprocessing step and preserves the computational advantages of mean-field variational Bayes, while ensuring accurate and reliable inference for the target parameter, including for uncertainty quantification. We investigate the numerical performance of our algorithm, showing that it performs competitively with existing methods. We further establish accompanying theoretical guarantees for estimation and uncertainty quantification in the form of a Bernstein--von Mises theorem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12659 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A variational Bayes approach to debiased inference for low-dimensional parameters in high-dimensional linear regression Castillo, Ismaël L'Huillier, Alice Ray, Kolyan Travis, Luke Machine Learning Statistics Theory 62 We propose a scalable variational Bayes method for statistical inference for a single or low-dimensional subset of the coordinates of a high-dimensional parameter in sparse linear regression. Our approach relies on assigning a mean-field approximation to the nuisance coordinates and carefully modelling the conditional distribution of the target given the nuisance. This requires only a preprocessing step and preserves the computational advantages of mean-field variational Bayes, while ensuring accurate and reliable inference for the target parameter, including for uncertainty quantification. We investigate the numerical performance of our algorithm, showing that it performs competitively with existing methods. We further establish accompanying theoretical guarantees for estimation and uncertainty quantification in the form of a Bernstein--von Mises theorem. |
| title | A variational Bayes approach to debiased inference for low-dimensional parameters in high-dimensional linear regression |
| topic | Machine Learning Statistics Theory 62 |
| url | https://arxiv.org/abs/2406.12659 |