Correspondence between neuroevolution and gradient descent.


Journal

Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555

Informations de publication

Date de publication:
02 11 2021
Historique:
received: 26 04 2021
accepted: 04 10 2021
entrez: 3 11 2021
pubmed: 4 11 2021
medline: 24 12 2021
Statut: epublish

Résumé

We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian white noise. Averaged over independent realizations of the learning process, neuroevolution is equivalent to gradient descent on the loss function. We use numerical simulation to show that this correspondence can be observed for finite mutations, for shallow and deep neural networks. Our results provide a connection between two families of neural-network training methods that are usually considered to be fundamentally different.

Identifiants

pubmed: 34728632
doi: 10.1038/s41467-021-26568-2
pii: 10.1038/s41467-021-26568-2
pmc: PMC8563972
doi:

Types de publication

Journal Article Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S.

Langues

eng

Sous-ensembles de citation

IM

Pagination

6317

Informations de copyright

© 2021. The Author(s).

Références

Biosystems. 1994;32(3):171-82
pubmed: 7919114
Eur Phys J E Soft Matter. 2018 May 14;41(5):59
pubmed: 29748868
Phys Rev E Stat Nonlin Soft Matter Phys. 2007 Jul;76(1 Pt 1):011507
pubmed: 17677450
J Chem Phys. 2007 Aug 28;127(8):085106
pubmed: 17764305
J Chem Phys. 2007 Oct 21;127(15):154101
pubmed: 17949126
J Chem Phys. 2010 May 21;132(19):194102
pubmed: 20499946
Phys Rev Lett. 1989 Jan 23;62(4):361-364
pubmed: 10040213
Evol Comput. 2002 Summer;10(2):99-127
pubmed: 12180173
Neural Netw. 2015 Jan;61:85-117
pubmed: 25462637
Phys Rev E. 2020 May;101(5-1):052604
pubmed: 32575260
Phys Rev Lett. 1987 Jan 12;58(2):86-88
pubmed: 10034599
J Chem Phys. 2013 Jun 28;138(24):244111
pubmed: 23822231
Phys Rev Lett. 2004 Jan 23;92(3):035504
pubmed: 14753886

Auteurs

Stephen Whitelam (S)

Molecular Foundry, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA, 94720, USA. swhitelam@lbl.gov.

Viktor Selin (V)

Department of Physics, University of Ottawa, Ottawa, ON, K1N 6N5, Canada.

Sang-Won Park (SW)

Molecular Foundry, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA, 94720, USA.

Isaac Tamblyn (I)

Department of Physics, University of Ottawa, Ottawa, ON, K1N 6N5, Canada. isaac.tamblyn@uottawa.ca.
National Research Council of Canada, Ottawa, ON, K1N 5A2, Canada. isaac.tamblyn@uottawa.ca.
Vector Institute for Artificial Intelligence, Toronto, ON, M5G 1M1, Canada. isaac.tamblyn@uottawa.ca.

Articles similaires

Selecting optimal software code descriptors-The case of Java.

Yegor Bugayenko, Zamira Kholmatova, Artem Kruglov et al.
1.00
Software Algorithms Programming Languages
T-Lymphocytes, Regulatory Lung Neoplasms Proto-Oncogene Proteins p21(ras) Animals Humans

Pathogenic mitochondrial DNA mutations inhibit melanoma metastasis.

Spencer D Shelton, Sara House, Luiza Martins Nascentes Melo et al.
1.00
DNA, Mitochondrial Humans Melanoma Mutation Neoplasm Metastasis

Prevalence and implications of fragile X premutation screening in Thailand.

Areerat Hnoonual, Sunita Kaewfai, Chanin Limwongse et al.
1.00
Humans Fragile X Mental Retardation Protein Thailand Male Female

Classifications MeSH