Fast Near-Optimal Estimation over Symmetric Norm Balls
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917553275666432 |
|---|---|
| author | Neykov, Matey |
| author_facet | Neykov, Matey |
| contents | This short note proposes a polynomial-time algorithm for near-optimal Euclidean estimation of a signal constrained to lie in the unit ball of a symmetric norm, where the symmetry is with respect to a known basis and the norm is accessible through an evaluation oracle. We further extend the method to a random-design, moderate-dimensional linear regression setting, where the regression parameter is likewise assumed to belong to a constraint set defined by a symmetric norm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01554 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fast Near-Optimal Estimation over Symmetric Norm Balls Neykov, Matey Statistics Theory This short note proposes a polynomial-time algorithm for near-optimal Euclidean estimation of a signal constrained to lie in the unit ball of a symmetric norm, where the symmetry is with respect to a known basis and the norm is accessible through an evaluation oracle. We further extend the method to a random-design, moderate-dimensional linear regression setting, where the regression parameter is likewise assumed to belong to a constraint set defined by a symmetric norm. |
| title | Fast Near-Optimal Estimation over Symmetric Norm Balls |
| topic | Statistics Theory |
| url | https://arxiv.org/abs/2606.01554 |