Journal article icon

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:
Publisher copy:
10.1016/j.physa.2021.126742

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Role:
Author
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
Language:
English
Keywords:
Pubs id:
1221536
Local pid:
pubs:1221536
Deposit date:
2021-12-06

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP