Journal article
Appearance of random matrix theory in deep learning
- Abstract:
- We investigate the local spectral statistics of the loss surface Hessians of artificial neural networks, where we discover agreement with Gaussian Orthogonal Ensemble statistics across several network architectures and datasets. These results shed new light on the applicability of Random Matrix Theory to modelling neural networks and suggest a role for it in the study of loss surfaces in deep learning.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 713.7KB, Terms of use)
-
- Publisher copy:
- 10.1016/j.physa.2021.126742
Authors
Bibliographic Details
- Publisher:
- Elsevier
- Journal:
- Physica A: Statistical Mechanics and its Applications More from this journal
- Volume:
- 590
- Article number:
- 126742
- Publication date:
- 2021-12-11
- Acceptance date:
- 2021-12-05
- DOI:
- ISSN:
-
0378-4371
Item Description
- Language:
-
English
- Keywords:
- Pubs id:
-
1221536
- Local pid:
-
pubs:1221536
- Deposit date:
-
2021-12-06
Terms of use
- Copyright holder:
- Elsevier B.V.
- Copyright date:
- 2021
- Rights statement:
- © 2021 Elsevier B.V. All rights reserved.
- Notes:
- This is the accepted manuscript version of the article. The final version is available online from Elsevier at: https://doi.org/10.1016/j.physa.2021.126742
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record