Concentration and moment inequalities for sums of independent heavy-tailed random matrices
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912717582893056 |
|---|---|
| author | Jirak, Moritz Minsker, Stanislav Shen, Yiqiu Wahl, Martin |
| author_facet | Jirak, Moritz Minsker, Stanislav Shen, Yiqiu Wahl, Martin |
| contents | We prove Fuk-Nagaev and Rosenthal-type inequalities for sums of independent random matrices, focusing on the situation when the norms of the matrices possess finite moments of only low orders. Our bounds depend on the ``intrinsic'' dimensional characteristics such as the effective rank, as opposed to the dimension of the ambient space. We illustrate the advantages of such results through several applications, including new moment inequalities for sample covariance matrices and their eigenvectors when the underlying distribution is heavy-tailed. Moreover, we demonstrate that our techniques yield sharpened versions of moment inequalities for empirical processes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12948 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Concentration and moment inequalities for sums of independent heavy-tailed random matrices Jirak, Moritz Minsker, Stanislav Shen, Yiqiu Wahl, Martin Probability Statistics Theory 60B20, 60E15, 62H25, 15A42 We prove Fuk-Nagaev and Rosenthal-type inequalities for sums of independent random matrices, focusing on the situation when the norms of the matrices possess finite moments of only low orders. Our bounds depend on the ``intrinsic'' dimensional characteristics such as the effective rank, as opposed to the dimension of the ambient space. We illustrate the advantages of such results through several applications, including new moment inequalities for sample covariance matrices and their eigenvectors when the underlying distribution is heavy-tailed. Moreover, we demonstrate that our techniques yield sharpened versions of moment inequalities for empirical processes. |
| title | Concentration and moment inequalities for sums of independent heavy-tailed random matrices |
| topic | Probability Statistics Theory 60B20, 60E15, 62H25, 15A42 |
| url | https://arxiv.org/abs/2407.12948 |