Asymptotic behavior of eigenvalues of large rank perturbations of large random matrices
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914490070597632 |
|---|---|
| author | Afanasiev, Ievgenii Berlyand, Leonid Kiyashko, Mariia |
| author_facet | Afanasiev, Ievgenii Berlyand, Leonid Kiyashko, Mariia |
| contents | The paper is concerned with deformed Wigner random matrices. These matrices are closely related to Deep Neural Networks (DNNs): weight matrices of trained DNNs could be represented in the form $R + S$, where $R$ is random and $S$ is highly correlated. The spectrum of such matrices plays a key role in rigorous underpinning of the novel pruning technique based on Random Matrix Theory. In practice, the spectrum of the matrix $S$ can be rather complicated. In this paper, we develop an asymptotic analysis for the case of full rank $S$ with increasing number of outlier eigenvalues. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12182 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Asymptotic behavior of eigenvalues of large rank perturbations of large random matrices Afanasiev, Ievgenii Berlyand, Leonid Kiyashko, Mariia Mathematical Physics Machine Learning Probability 60B20, 15B52 The paper is concerned with deformed Wigner random matrices. These matrices are closely related to Deep Neural Networks (DNNs): weight matrices of trained DNNs could be represented in the form $R + S$, where $R$ is random and $S$ is highly correlated. The spectrum of such matrices plays a key role in rigorous underpinning of the novel pruning technique based on Random Matrix Theory. In practice, the spectrum of the matrix $S$ can be rather complicated. In this paper, we develop an asymptotic analysis for the case of full rank $S$ with increasing number of outlier eigenvalues. |
| title | Asymptotic behavior of eigenvalues of large rank perturbations of large random matrices |
| topic | Mathematical Physics Machine Learning Probability 60B20, 15B52 |
| url | https://arxiv.org/abs/2507.12182 |