Journal article icon

Journal article

Mean field analysis of neural networks: a central limit theorem

Abstract:

We rigorously prove a central limit theorem for neural network models with a single hidden layer. The central limit theorem is proven in the asymptotic regime of simultaneously (A) large numbers of hidden units and (B) large numbers of stochastic gradient descent training iterations. Our result describes the neural network’s fluctuations around its mean-field limit. The fluctuations have a Gaussian distribution and satisfy a stochastic partial differential equation. The proof relies upon weak...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1016/j.spa.2019.06.003

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Role:
Author
Publisher:
Elsevier Publisher's website
Journal:
Stochastic Processes and their Applications Journal website
Volume:
130
Issue:
3
Pages:
1820-1852
Publication date:
2019-06-12
Acceptance date:
2020-06-03
DOI:
ISSN:
0304-4149
Language:
English
Pubs id:
1124852
Local pid:
pubs:1124852
Deposit date:
2020-08-10

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