Entrywise application of non-linear functions on orthogonally invariant matrices
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913607332134912 |
|---|---|
| author | Speicher, Roland Wendel, Alexander |
| author_facet | Speicher, Roland Wendel, Alexander |
| contents | In this article, we investigate how the entrywise application of a non-linear function to symmetric orthogonally invariant random matrix ensembles alters the spectral distribution. We treat also the multivariate case where we apply multivariate functions to entries of several orthogonally invariant matrices; where even correlations between the matrices are allowed. We find that in all those cases a Gaussian equivalence principle holds, that is, the asymptotic effect of the non-linear function is the same as taking a linear combination of the involved matrices and an additional independent GOE. The ReLU-function in the case of one matrix and the max-function in the case of two matrices provide illustrative examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06943 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Entrywise application of non-linear functions on orthogonally invariant matrices Speicher, Roland Wendel, Alexander Spectral Theory Statistical Mechanics Machine Learning Operator Algebras In this article, we investigate how the entrywise application of a non-linear function to symmetric orthogonally invariant random matrix ensembles alters the spectral distribution. We treat also the multivariate case where we apply multivariate functions to entries of several orthogonally invariant matrices; where even correlations between the matrices are allowed. We find that in all those cases a Gaussian equivalence principle holds, that is, the asymptotic effect of the non-linear function is the same as taking a linear combination of the involved matrices and an additional independent GOE. The ReLU-function in the case of one matrix and the max-function in the case of two matrices provide illustrative examples. |
| title | Entrywise application of non-linear functions on orthogonally invariant matrices |
| topic | Spectral Theory Statistical Mechanics Machine Learning Operator Algebras |
| url | https://arxiv.org/abs/2412.06943 |