Simple view
Full metadata view
Authors
Statistics
Gradient estimators for normalizing flows
Recently, a machine learning approach to Monte-Carlo simulations called Neural Markov Chain Monte Carlo (NMCMC) is gaining traction. In its most popular form, it uses neural networks to construct normalizing flows which are then trained to approximate the desired target distribution. In this contribution, we present a new gradient estimator for the Stochastic Gradient Descent algorithm (and the corresponding PyTorch implementation) and show that it leads to better training results for the model. For this model, our estimator achieves the same precision in approximately half of the time needed in the standard approach and ultimately provides better estimates of the free energy. We attribute this effect to the lower variance of the new estimator. In contrary to the standard learning algorithm, our approach does not require estimation of the action gradient with respect to the fields, thus has the potential of further speeding up the training for models with more complicated actions.
cris.lastimport.scopus | 2024-04-24T04:56:09Z | |
dc.abstract.en | Recently, a machine learning approach to Monte-Carlo simulations called Neural Markov Chain Monte Carlo (NMCMC) is gaining traction. In its most popular form, it uses neural networks to construct normalizing flows which are then trained to approximate the desired target distribution. In this contribution, we present a new gradient estimator for the Stochastic Gradient Descent algorithm (and the corresponding PyTorch implementation) and show that it leads to better training results for the model. For this model, our estimator achieves the same precision in approximately half of the time needed in the standard approach and ultimately provides better estimates of the free energy. We attribute this effect to the lower variance of the new estimator. In contrary to the standard learning algorithm, our approach does not require estimation of the action gradient with respect to the fields, thus has the potential of further speeding up the training for models with more complicated actions. | |
dc.affiliation | Wydział Fizyki, Astronomii i Informatyki Stosowanej : Instytut Informatyki Stosowanej | |
dc.affiliation | Wydział Fizyki, Astronomii i Informatyki Stosowanej : Instytut Fizyki Teoretycznej | |
dc.contributor.author | Białas, Piotr - 127296 | |
dc.contributor.author | Korcyl, Piotr - 125645 | |
dc.contributor.author | Stebel, Tomasz - 150140 | |
dc.date.accessioned | 2024-04-19T10:43:13Z | |
dc.date.available | 2024-04-19T10:43:13Z | |
dc.date.issued | 2024 | |
dc.date.openaccess | 0 | |
dc.description.accesstime | w momencie opublikowania | |
dc.description.number | 3 | |
dc.description.version | ostateczna wersja wydawcy | |
dc.description.volume | 55 | |
dc.identifier.articleid | A2 | |
dc.identifier.doi | 10.5506/APhysPolB.55.3-A2 | |
dc.identifier.issn | 0587-4254 | |
dc.identifier.issn | 1509-5770 | |
dc.identifier.uri | https://ruj.uj.edu.pl/handle/item/330601 | |
dc.language | eng | |
dc.language.container | eng | |
dc.relation.ispartof | Acta Physica Polonica B | |
dc.rights | Udzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa | |
dc.rights.licence | CC-BY | |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/legalcode.pl | |
dc.share.type | otwarte czasopismo | |
dc.subtype | Article | |
dc.title | Gradient estimators for normalizing flows | |
dc.title.journal | Acta Physica Polonica, Series B. | |
dc.type | JournalArticle | |
dspace.entity.type | Publication | en |
oaire.citation.issue | 3 | |
oaire.citation.volume | 55 |
* The migration of download and view statistics prior to the date of April 8, 2024 is in progress.
Views
14
Views per month
Views per city
Downloads
Open Access
License
Except as otherwise noted, this item is licensed under the Attribution 4.0 International licence