Mean Field Initialization of the Annealed Importance Sampling Algorithm for an Efficient Evaluation of the Partition Function Using Restricted Boltzmann Machines

Probabilistic models in physics often require the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function Z. Obtaining the exact value of Z, though, becomes a forbiddingly expensive task as the system size increases. A possible way to tackle this p...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Entropy (Basel, Switzerland) Ročník 27; číslo 2; s. 171
Hlavní autori: Prat Pou, Arnau, Romero, Enrique, Martí, Jordi, Mazzanti, Ferran
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Switzerland MDPI AG 06.02.2025
MDPI
Predmet:
ISSN:1099-4300, 1099-4300
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Probabilistic models in physics often require the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function Z. Obtaining the exact value of Z, though, becomes a forbiddingly expensive task as the system size increases. A possible way to tackle this problem is to use the Annealed Importance Sampling (AIS) algorithm, which provides a tool to stochastically estimate the partition function of the system. The nature of AIS allows for an efficient and parallel implementation in Restricted Boltzmann Machines (RBMs). In this work, we evaluate the partition function of magnetic spin and spin-like systems mapped into RBMs using AIS. So far, the standard application of the AIS algorithm starts from the uniform probability distribution and uses a large number of Monte Carlo steps to obtain reliable estimations of Z following an annealing process. We show that both the quality of the estimation and the cost of the computation can be significantly improved by using a properly selected mean-field starting probability distribution. We perform a systematic analysis of AIS in both small- and large-sized problems, and compare the results to exact values in problems where these are known. As a result, we propose two successful strategies that work well in all the problems analyzed. We conclude that these are good starting points to estimate the partition function with AIS with a relatively low computational cost. The procedures presented are not linked to any learning process, and therefore do not require a priori knowledge of a training dataset.
AbstractList Probabilistic models in physics often require the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function Z. Obtaining the exact value of Z, though, becomes a forbiddingly expensive task as the system size increases. A possible way to tackle this problem is to use the Annealed Importance Sampling (AIS) algorithm, which provides a tool to stochastically estimate the partition function of the system. The nature of AIS allows for an efficient and parallel implementation in Restricted Boltzmann Machines (RBMs). In this work, we evaluate the partition function of magnetic spin and spin-like systems mapped into RBMs using AIS. So far, the standard application of the AIS algorithm starts from the uniform probability distribution and uses a large number of Monte Carlo steps to obtain reliable estimations of Z following an annealing process. We show that both the quality of the estimation and the cost of the computation can be significantly improved by using a properly selected mean-field starting probability distribution. We perform a systematic analysis of AIS in both small- and large-sized problems, and compare the results to exact values in problems where these are known. As a result, we propose two successful strategies that work well in all the problems analyzed. We conclude that these are good starting points to estimate the partition function with AIS with a relatively low computational cost. The procedures presented are not linked to any learning process, and therefore do not require a priori knowledge of a training dataset.
Probabilistic models in physics often require the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function Z. Obtaining the exact value of Z, though, becomes a forbiddingly expensive task as the system size increases. A possible way to tackle this problem is to use the Annealed Importance Sampling (AIS) algorithm, which provides a tool to stochastically estimate the partition function of the system. The nature of AIS allows for an efficient and parallel implementation in Restricted Boltzmann Machines (RBMs). In this work, we evaluate the partition function of magnetic spin and spin-like systems mapped into RBMs using AIS. So far, the standard application of the AIS algorithm starts from the uniform probability distribution and uses a large number of Monte Carlo steps to obtain reliable estimations of Z following an annealing process. We show that both the quality of the estimation and the cost of the computation can be significantly improved by using a properly selected mean-field starting probability distribution. We perform a systematic analysis of AIS in both small- and large-sized problems, and compare the results to exact values in problems where these are known. As a result, we propose two successful strategies that work well in all the problems analyzed. We conclude that these are good starting points to estimate the partition function with AIS with a relatively low computational cost. The procedures presented are not linked to any learning process, and therefore do not require a priori knowledge of a training dataset.Probabilistic models in physics often require the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function Z. Obtaining the exact value of Z, though, becomes a forbiddingly expensive task as the system size increases. A possible way to tackle this problem is to use the Annealed Importance Sampling (AIS) algorithm, which provides a tool to stochastically estimate the partition function of the system. The nature of AIS allows for an efficient and parallel implementation in Restricted Boltzmann Machines (RBMs). In this work, we evaluate the partition function of magnetic spin and spin-like systems mapped into RBMs using AIS. So far, the standard application of the AIS algorithm starts from the uniform probability distribution and uses a large number of Monte Carlo steps to obtain reliable estimations of Z following an annealing process. We show that both the quality of the estimation and the cost of the computation can be significantly improved by using a properly selected mean-field starting probability distribution. We perform a systematic analysis of AIS in both small- and large-sized problems, and compare the results to exact values in problems where these are known. As a result, we propose two successful strategies that work well in all the problems analyzed. We conclude that these are good starting points to estimate the partition function with AIS with a relatively low computational cost. The procedures presented are not linked to any learning process, and therefore do not require a priori knowledge of a training dataset.
Probabilistic models in physics often require the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function . Obtaining the exact value of , though, becomes a forbiddingly expensive task as the system size increases. A possible way to tackle this problem is to use the Annealed Importance Sampling (AIS) algorithm, which provides a tool to stochastically estimate the partition function of the system. The nature of AIS allows for an efficient and parallel implementation in Restricted Boltzmann Machines (RBMs). In this work, we evaluate the partition function of magnetic spin and spin-like systems mapped into RBMs using AIS. So far, the standard application of the AIS algorithm starts from the uniform probability distribution and uses a large number of Monte Carlo steps to obtain reliable estimations of following an annealing process. We show that both the quality of the estimation and the cost of the computation can be significantly improved by using a properly selected mean-field starting probability distribution. We perform a systematic analysis of AIS in both small- and large-sized problems, and compare the results to exact values in problems where these are known. As a result, we propose two successful strategies that work well in all the problems analyzed. We conclude that these are good starting points to estimate the partition function with AIS with a relatively low computational cost. The procedures presented are not linked to any learning process, and therefore do not require a priori knowledge of a training dataset.
Audience Academic
Author Martí, Jordi
Mazzanti, Ferran
Prat Pou, Arnau
Romero, Enrique
AuthorAffiliation 2 Departament de Ciències de la Computació, Universitat Politècnica de Catalunya, Barcelona Tech, Campus Nord B4-B5, E-08034 Barcelona, Spain; eromero@cs.upc.edu
1 Departament de Física, Universitat Politècnica de Catalunya, Barcelona Tech, Campus Nord B4-B5, E-08034 Barcelona, Spain; arnau.prat.pou@upc.edu (A.P.P.); jordi.marti@upc.edu (J.M.)
AuthorAffiliation_xml – name: 1 Departament de Física, Universitat Politècnica de Catalunya, Barcelona Tech, Campus Nord B4-B5, E-08034 Barcelona, Spain; arnau.prat.pou@upc.edu (A.P.P.); jordi.marti@upc.edu (J.M.)
– name: 2 Departament de Ciències de la Computació, Universitat Politècnica de Catalunya, Barcelona Tech, Campus Nord B4-B5, E-08034 Barcelona, Spain; eromero@cs.upc.edu
Author_xml – sequence: 1
  givenname: Arnau
  orcidid: 0000-0002-1770-9636
  surname: Prat Pou
  fullname: Prat Pou, Arnau
– sequence: 2
  givenname: Enrique
  surname: Romero
  fullname: Romero, Enrique
– sequence: 3
  givenname: Jordi
  orcidid: 0000-0002-3721-9634
  surname: Martí
  fullname: Martí, Jordi
– sequence: 4
  givenname: Ferran
  surname: Mazzanti
  fullname: Mazzanti, Ferran
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40003168$$D View this record in MEDLINE/PubMed
BookMark eNplks1uEzEQx1eoiH7AgRdAK3GBQ1p_7K7tEwpVApFagYCerVmvnTjy2sHrrUTfhjfFSdqqKfLB1sx_fjOemdPiyAevi-ItRueUCnShCUMEYYZfFCcYCTGpKEJHT97HxekwrBEilODmVXFcIYQobvhJ8fdagy_nVruuXHibLDh7B8kGXwZTppUup95rcDq7-02ICbzS5U_oN876ZTl1yxBtWvWlCbHMpJkxVlntUzm7BTcekL5DTHZnmI9e7R43w5byQw8pWpVyks_BpbsevC-vQa2s18Pr4qUBN-g39_dZcTOf_br8Orn69mVxOb2aqJrVaaKJ4agzrWAEFBFN3XRKVUzXjDAwGCvAGLq2qRHhShmoSasqgZjRiihAnJ4Viz23C7CWm2h7iH9kACt3hhCXclu_clpy3hCGScsJdFVFeatNZXJDDQNOWtZm1qc9azO2ve5U7kcEdwA99Hi7kstwKzHmNRV1kwkf7gkx_B5zf2RvB6WdA6_DOEiap00Zxw3L0vfPpOswRp97tVUhgbdzz6rzvWqZhymtNyEnVvl0urcq75Ox2T7lRHAqBMY54N3TPzwW_7A7WXCxF6gYhiFqI5VNu4FnsnUSI7ndTvm4nTni47OIB-j_2n_yy-Xu
CitedBy_id crossref_primary_10_7566_JPSJ_94_094007
Cites_doi 10.1016/j.neunet.2012.06.003
10.1103/RevModPhys.67.279
10.1119/1.1707017
10.1126/science.1127647
10.1145/1273496.1273596
10.1017/CBO9780511623257
10.1162/neco_a_01420
10.1023/A:1008923215028
10.1063/1.4907883
10.1007/BF02980577
10.1103/PhysRevLett.96.120201
10.7551/mitpress/5236.001.0001
10.1016/j.artint.2019.103195
10.1016/j.jcp.2011.12.008
10.1103/PhysRev.65.117
10.1103/PhysRevLett.110.210603
10.1016/j.cpc.2010.10.031
10.1142/9789813232105_0006
10.1103/PhysRevE.103.013302
10.1016/0021-9991(76)90078-4
10.1561/2200000006
10.1103/PhysRevB.100.064304
10.1063/1.481926
10.1093/oso/9780198513940.001.0001
10.1103/PhysRevE.106.024127
10.1119/1.18168
10.1007/978-3-662-05052-1_5
10.21468/SciPostPhys.16.4.095
10.1073/pnas.1505664112
10.1103/PhysRevE.81.016707
10.1109/TPAMI.1984.4767596
ContentType Journal Article
Copyright COPYRIGHT 2025 MDPI AG
2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
2025 by the authors. 2025
Copyright_xml – notice: COPYRIGHT 2025 MDPI AG
– notice: 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: 2025 by the authors. 2025
DBID AAYXX
CITATION
NPM
7TB
8FD
8FE
8FG
ABJCF
ABUWG
AFKRA
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FR3
HCIFZ
KR7
L6V
M7S
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
7X8
5PM
DOA
DOI 10.3390/e27020171
DatabaseName CrossRef
PubMed
Mechanical & Transportation Engineering Abstracts
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni Edition)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
ProQuest Technology Collection
ProQuest One Community College
ProQuest Central Korea
Engineering Research Database
SciTech Premium Collection
Civil Engineering Abstracts
ProQuest Engineering Collection
Engineering Database
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
Publicly Available Content Database
Technology Collection
Technology Research Database
ProQuest One Academic Middle East (New)
Mechanical & Transportation Engineering Abstracts
ProQuest Central Essentials
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest Central Korea
ProQuest Central (New)
Engineering Collection
Civil Engineering Abstracts
Engineering Database
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest One Academic UKI Edition
Materials Science & Engineering Collection
Engineering Research Database
ProQuest One Academic
ProQuest One Academic (New)
MEDLINE - Academic
DatabaseTitleList Publicly Available Content Database
CrossRef
MEDLINE - Academic


PubMed

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
EISSN 1099-4300
ExternalDocumentID oai_doaj_org_article_8862712b82ad4438bef4f031f7a82b7b
PMC11853956
A829839911
40003168
10_3390_e27020171
Genre Journal Article
GeographicLocations New York
United States
GeographicLocations_xml – name: New York
– name: United States
GrantInformation_xml – fundername: Generalitat de Catalunya for the grant Grup de Recerca SGR-Cat2021 Condensed, Complex and Quantum Matter Group
  grantid: 2021SGR-0141
– fundername: Ministerio de Ciencia e Innovación MCIN/AEI/10.13039/501100011033 (Spain)
  grantid: PID2023-147469NB-C21; PID2021-124297NB-C32; PID2022-143299OB-I00
GroupedDBID 29G
2WC
5GY
5VS
8FE
8FG
AADQD
AAFWJ
AAYXX
ABDBF
ABJCF
ACIWK
ACUHS
ADBBV
AEGXH
AENEX
AFFHD
AFKRA
AFPKN
AFZYC
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BENPR
BGLVJ
CCPQU
CITATION
CS3
DU5
E3Z
ESX
F5P
GROUPED_DOAJ
GX1
HCIFZ
HH5
IAO
ITC
J9A
KQ8
L6V
M7S
MODMG
M~E
OK1
OVT
PGMZT
PHGZM
PHGZT
PIMPY
PQGLB
PROAC
PTHSS
RNS
RPM
TR2
TUS
XSB
~8M
NPM
7TB
8FD
ABUWG
AZQEC
DWQXO
FR3
KR7
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
7X8
5PM
ID FETCH-LOGICAL-c575t-e2f80dfb972ac29656dcc47e5727af11ca11adb65028ccfa52bc4907fec2ca083
IEDL.DBID M7S
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001431601300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1099-4300
IngestDate Fri Oct 03 12:50:25 EDT 2025
Tue Nov 04 02:05:21 EST 2025
Sun Nov 09 09:48:04 EST 2025
Fri Jul 25 12:09:22 EDT 2025
Tue Nov 04 18:12:43 EST 2025
Mon Jul 21 06:01:47 EDT 2025
Tue Nov 18 21:03:48 EST 2025
Sat Nov 29 07:15:46 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords annealed importance sampling
magnetic systems
Restricted Boltzmann Machines
partition function
Language English
License Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c575t-e2f80dfb972ac29656dcc47e5727af11ca11adb65028ccfa52bc4907fec2ca083
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-3721-9634
0000-0002-1770-9636
OpenAccessLink https://www.proquest.com/docview/3170910023?pq-origsite=%requestingapplication%
PMID 40003168
PQID 3170910023
PQPubID 2032401
ParticipantIDs doaj_primary_oai_doaj_org_article_8862712b82ad4438bef4f031f7a82b7b
pubmedcentral_primary_oai_pubmedcentral_nih_gov_11853956
proquest_miscellaneous_3171378167
proquest_journals_3170910023
gale_infotracacademiconefile_A829839911
pubmed_primary_40003168
crossref_citationtrail_10_3390_e27020171
crossref_primary_10_3390_e27020171
PublicationCentury 2000
PublicationDate 20250206
PublicationDateYYYYMMDD 2025-02-06
PublicationDate_xml – month: 2
  year: 2025
  text: 20250206
  day: 6
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
– name: Basel
PublicationTitle Entropy (Basel, Switzerland)
PublicationTitleAlternate Entropy (Basel)
PublicationYear 2025
Publisher MDPI AG
MDPI
Publisher_xml – name: MDPI AG
– name: MDPI
References Giovannelli (ref_18) 2015; 142
Bengio (ref_12) 2009; 2
Yasuda (ref_20) 2022; 106
Krause (ref_14) 2020; 278
Rota (ref_25) 2010; 81
Zhou (ref_7) 2006; 96
ref_13
ref_11
Weigel (ref_15) 2011; 182
ref_10
Hinton (ref_28) 2006; 313
ref_32
Decelle (ref_36) 2024; 16
ref_31
Geman (ref_30) 1984; 6
Ising (ref_38) 1925; 31
ref_19
Rrapaj (ref_37) 2021; 103
ref_17
ref_39
Landau (ref_6) 2004; 72
Weigel (ref_16) 2012; 231
Bennett (ref_5) 1976; 22
Cossu (ref_35) 2019; 100
Ceperley (ref_22) 1996; 67
Sarsa (ref_24) 2000; 113
ref_21
Kosztin (ref_23) 1996; 64
ref_42
ref_41
ref_1
ref_3
Goldberg (ref_4) 2015; 112
ref_2
ref_29
ref_27
ref_26
Onsager (ref_40) 1944; 65
Vogel (ref_8) 2013; 110
Barra (ref_33) 2021; 34
Neal (ref_9) 2001; 11
Bulso (ref_34) 2021; 33
References_xml – volume: 34
  start-page: 1
  year: 2021
  ident: ref_33
  article-title: On the equivalence of Hopfield networks and Boltzmann machines
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2012.06.003
– volume: 67
  start-page: 279
  year: 1996
  ident: ref_22
  article-title: Path integrals in the theory of condensed helium
  publication-title: Rev. Mod. Phys.
  doi: 10.1103/RevModPhys.67.279
– volume: 72
  start-page: 1294
  year: 2004
  ident: ref_6
  article-title: A new approach to Monte Carlo simulations in statistical physics: Wang-Landau sampling
  publication-title: Am. J. Phys.
  doi: 10.1119/1.1707017
– volume: 313
  start-page: 504
  year: 2006
  ident: ref_28
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
  doi: 10.1126/science.1127647
– ident: ref_29
  doi: 10.1145/1273496.1273596
– ident: ref_32
– ident: ref_3
– ident: ref_27
  doi: 10.1017/CBO9780511623257
– volume: 33
  start-page: 2646
  year: 2021
  ident: ref_34
  article-title: Restricted Boltzmann machines as models of interacting variables
  publication-title: Neural Comput.
  doi: 10.1162/neco_a_01420
– volume: 11
  start-page: 125
  year: 2001
  ident: ref_9
  article-title: Annealed Importance Sampling
  publication-title: Stat. Comput.
  doi: 10.1023/A:1008923215028
– volume: 142
  start-page: 074102
  year: 2015
  ident: ref_18
  article-title: Annealed importance sampling with constant cooling rate
  publication-title: J. Chem. Phys.
  doi: 10.1063/1.4907883
– volume: 31
  start-page: 253
  year: 1925
  ident: ref_38
  article-title: Contribution to the theory of ferromagnetism
  publication-title: Z. Phys.
  doi: 10.1007/BF02980577
– volume: 96
  start-page: 120201
  year: 2006
  ident: ref_7
  article-title: Wang-Landau Algorithm for Continuous Models and Joint Density of States
  publication-title: Phys. Rev. Lett.
  doi: 10.1103/PhysRevLett.96.120201
– ident: ref_11
  doi: 10.7551/mitpress/5236.001.0001
– volume: 278
  start-page: 103195
  year: 2020
  ident: ref_14
  article-title: Algorithms for estimating the partition function of restricted Boltzmann machines
  publication-title: Artif. Intell.
  doi: 10.1016/j.artint.2019.103195
– ident: ref_42
– ident: ref_1
– volume: 231
  start-page: 3064
  year: 2012
  ident: ref_16
  article-title: Performance potential for simulating spin models on GPU
  publication-title: J. Comput. Phys.
  doi: 10.1016/j.jcp.2011.12.008
– volume: 65
  start-page: 117
  year: 1944
  ident: ref_40
  article-title: Crystal statistics. I. A two-dimensional model with an order-disorder transition
  publication-title: Phys. Rev.
  doi: 10.1103/PhysRev.65.117
– ident: ref_21
– volume: 110
  start-page: 210603
  year: 2013
  ident: ref_8
  article-title: Generic, Hierarchical Framework for Massively Parallel Wang-Landau Sampling
  publication-title: Phys. Rev. Lett.
  doi: 10.1103/PhysRevLett.110.210603
– volume: 182
  start-page: 1833
  year: 2011
  ident: ref_15
  article-title: Simulating spin models on GPU
  publication-title: Comput. Phys. Commun.
  doi: 10.1016/j.cpc.2010.10.031
– ident: ref_17
  doi: 10.1142/9789813232105_0006
– volume: 103
  start-page: 013302
  year: 2021
  ident: ref_37
  article-title: Exact representations of many-body interactions with restricted-Boltzmann-machine neural networks
  publication-title: Phys. Rev. E
  doi: 10.1103/PhysRevE.103.013302
– volume: 22
  start-page: 245
  year: 1976
  ident: ref_5
  article-title: Efficient Estimation of Free Energy Differences from Monte Carlo Data
  publication-title: J. Comp. Phys.
  doi: 10.1016/0021-9991(76)90078-4
– ident: ref_31
– volume: 2
  start-page: 1
  year: 2009
  ident: ref_12
  article-title: Learning deep architectures for AI
  publication-title: Found. Trends Mach. Learn.
  doi: 10.1561/2200000006
– ident: ref_2
– ident: ref_10
– volume: 100
  start-page: 064304
  year: 2019
  ident: ref_35
  article-title: Machine learning determination of dynamical parameters: The Ising model case
  publication-title: Phys. Rev. B
  doi: 10.1103/PhysRevB.100.064304
– volume: 113
  start-page: 1366
  year: 2000
  ident: ref_24
  article-title: A path integral ground state method
  publication-title: J. Chem. Phys.
  doi: 10.1063/1.481926
– ident: ref_39
  doi: 10.1093/oso/9780198513940.001.0001
– ident: ref_41
– ident: ref_13
– volume: 106
  start-page: 024127
  year: 2022
  ident: ref_20
  article-title: Free energy evaluation using marginalized annealed importance sampling
  publication-title: Phys. Rev. E
  doi: 10.1103/PhysRevE.106.024127
– ident: ref_19
– volume: 64
  start-page: 63
  year: 1996
  ident: ref_23
  article-title: Introduction to the diffusion Monte Carlo method
  publication-title: Am. J. Phys.
  doi: 10.1119/1.18168
– ident: ref_26
  doi: 10.1007/978-3-662-05052-1_5
– volume: 16
  start-page: 095
  year: 2024
  ident: ref_36
  article-title: Inferring effective couplings with restricted Boltzmann machines
  publication-title: SciPost Phys.
  doi: 10.21468/SciPostPhys.16.4.095
– volume: 112
  start-page: 13161
  year: 2015
  ident: ref_4
  article-title: A complexity classification of spin systems with an external field
  publication-title: Proc. Natl. Acad. Sci. USA
  doi: 10.1073/pnas.1505664112
– volume: 81
  start-page: 016707
  year: 2010
  ident: ref_25
  article-title: High-order time expansion path integral ground state
  publication-title: Phys. Rev. E
  doi: 10.1103/PhysRevE.81.016707
– volume: 6
  start-page: 721
  year: 1984
  ident: ref_30
  article-title: Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.1984.4767596
SSID ssj0023216
Score 2.373874
Snippet Probabilistic models in physics often require the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function...
Probabilistic models in physics often require the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function ....
SourceID doaj
pubmedcentral
proquest
gale
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 171
SubjectTerms Algorithms
annealed importance sampling
Annealing
Computing costs
Energy
Importance sampling
magnetic systems
Monte Carlo simulation
partition function
Partitions (mathematics)
Probabilistic models
Probability
Probability distribution
Restricted Boltzmann Machines
Statistical analysis
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Li9swEBZl6aGX0tKX221RS6G9mLVkxZKP2ZLQHnZZ-oC9mZEs7QYSuyTeHvbf7D_tjOyYmBZ66SUYa3BkzWjmGzz6hrH33hSFU16l6AJDqgoHaWltSEvjyjwD_LUQm03o83NzeVleHLT6opqwnh64X7gTg5BbC2mNhFqp3FgfVEBLDBqMtNqS9810uU-mhlQrl6LoeYRyTOpPPJ26ImaYSfSJJP1_uuKDWDStkzwIPMtH7OGAGPm8n-ljds83T9jdmYeGL6n8jH-h-h9YDwcqeRs4gjo-RweK_4jDmwixUbn8G1D9eHPF5-urdrvqrjccMSvHJy0ikwROgC9G-u_9ky5okeKNJQbBeBELDfhXT00_HGJWftquu9sNNA0_i9WZfveU_Vguvn_6nA7dFlKHkK1LvQwmq4MttQQnS8R5tXNK-xkiHAhCOBACaouIThrnAsykdQpT6-CddIBI7hk7atrGv2BcoHka0JlzWY0ihbX0MVFAXmh0H7M8YR_3WqjcQEVOHTHWFaYkpLBqVFjC3o2iP3v-jb8JnZIqRwGizI430JCqwZCqfxlSwj6QIVS0sXEyDobzCfhKRJFVzY0sEU1icEjY8d5WqmHH7yrEYQS90PQS9nYcxr1KH2Cg8e1NlBG5NqLQCXvem9Y4Z0XZqShMwszE6CYvNR1pVteRD1wQ5sI89-X_WIZX7IGkFsdUmF4cs6Nue-Nfs_vuV7fabd_EXfYbmL0wKw
  priority: 102
  providerName: Directory of Open Access Journals
Title Mean Field Initialization of the Annealed Importance Sampling Algorithm for an Efficient Evaluation of the Partition Function Using Restricted Boltzmann Machines
URI https://www.ncbi.nlm.nih.gov/pubmed/40003168
https://www.proquest.com/docview/3170910023
https://www.proquest.com/docview/3171378167
https://pubmed.ncbi.nlm.nih.gov/PMC11853956
https://doaj.org/article/8862712b82ad4438bef4f031f7a82b7b
Volume 27
WOSCitedRecordID wos001431601300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1099-4300
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023216
  issn: 1099-4300
  databaseCode: DOA
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1099-4300
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023216
  issn: 1099-4300
  databaseCode: M~E
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Engineering Database
  customDbUrl:
  eissn: 1099-4300
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023216
  issn: 1099-4300
  databaseCode: M7S
  dateStart: 19990301
  isFulltext: true
  titleUrlDefault: http://search.proquest.com
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1099-4300
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023216
  issn: 1099-4300
  databaseCode: BENPR
  dateStart: 19990301
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 1099-4300
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023216
  issn: 1099-4300
  databaseCode: PIMPY
  dateStart: 19990301
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwEB6xuxy48BCPDSyVQUhwibZ20tg5oRa1Yg-tql2QyimyHbu7UpssbZcDB_4L_5QZNw1bgbhwiarYSsfyeOYbe_wNwBunssymLo3RBPo4zayOc2N8nCubJ12NT6NDsQk5majZLJ82G27rJq1yZxODoS5rS3vkp-jnyLWhi3l__TWmqlF0utqU0DiAI2JJ4CF176INuBLBsy2bUIKh_amju1fED7PngwJV_58G-ZZH2s-WvOV-Rg_-V_CHcL8Bnqy_1ZRHcMdVj-Hn2OmKjSiLjZ1RGpFeNPcyWe0ZYkPWRzuMImPzMiB11BF2oSkNvZqz_mKO_7S5XDKEvgy_NAyEFDgCNmxZxHdfmpKShhcj9KXhR8hXYOeOaodYhL5sUC8235e6qtg4JHm69RP4PBp--vAxboo2xBaR3yZ2wqtu6U0uhbYiR7hYWptK10OgpD3nVnOuS4PAUChrve4JY1OM0L2zwmoEhE_hsKordwyMo5YrLbvWdkvskhlDZ5JcJ5lEK9RLIni3m8bCNozmVFhjUWBkQzNetDMeweu26_WWxuNvnQakC20HYt4OL-rVvGgWcqEwBJRcGCV0maaJMs6nHi2jl1oJI00Eb0mTCrIPKIzVzTUHHBIxbRV9JXIEpehjIjjZKUzRGI518VtbInjVNuOSp3McXbn6JvThiVQ8kxE82-pmK3NKQS7PVARqT2v3BrXfUl1dBlpxTtANw-Xn_5brBdwTVAOZMtezEzjcrG7cS7hrv22u1qsOHMiZ6sDRYDiZnnfCDkcnLEp6_hhiy_RsPP3yC_5TRK4
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1fb9MwED-NgQQv_BH_AgMMAsFLtNpJE-cBoQ5abdpaTWxIe8tsx-4mtcloOxB8G74An5E7NwmrQLztgZcoii3Ldu_u97v6fAfw0sokMbGNQzSBLowTo8JMaxdm0mRRR-FTK19sIh2N5NFRtr8GP5u7MBRW2dhEb6iLytB_5JuIcwRtCDHvzj6HVDWKTlebEhpLsdi1376iyzZ_u_MBf99XQgz6h--3w7qqQGiQmixCK5zsFE5nqVBGZMhnCmPi1HYRyZXj3CjOVaGRuQhpjFNdoU2MLqSzRhiFjAXHvQJXkUaIzIcKHrQOXiR4ssxeFEVZZ9PSXS_KR7OCeb40wJ8AcAEBV6MzL8Dd4Nb_tlG34WZNrFlvqQl3YM2Wd-HH0KqSDShKj-1QmJSa1PdOWeUYcl_WQ5zBLcLmqfdEUAfYgaIw-3LMepMxrmxxMmVI7RmO1PcJN3DHWL_Nkt6MtE9K6D8MkCv4Fx-PwT5aqo1ikNqzrWqy-D5VZcmGPojVzu_Bp0vZlfuwXlalfQiMoxZLlXaM6RTYJdGazly5ipIUrWw3CuBNIza5qTO2U-GQSY6eG0lY3kpYAC_armfLNCV_67RFstd2oMzi_kM1G-e1ocolurgpF1oKVcRxJLV1sUPL71IlhU51AK9JcnOyfzgZo-prHLgkyiSW96TIkHQjhgaw0QhoXhvGef5bOgN43jajSaNzKlXa6tz34VEqeZIG8GCpC-2cY3LieSIDkCtasrKo1Zby9MSnTedETbNu8ujf83oG17cPh3v53s5o9zHcEFTvmaL0kw1YX8zO7RO4Zr4sTuezp175GRxfthL9AuzHnak
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwEB4tXYS48BCvwAIGgeASbe2kiXNAqMu2olpaVTyk5RRsx-6u1CZL2wXBv-Fv8OuYcdOwFYjbHrhEUWxZtjsz3zf1eAbgiZVJYmIbh2gCXRgnRoWZ1i7MpMmitsKnVr7YRDoaycPDbLwFP9d3YSiscm0TvaEuKkP_ke8izhG0UVoeV4dFjPf7L08-h1RBik5a1-U0ViJyYL99Rfdt8WKwj7_1UyH6vfevXod1hYHQIE1ZhlY42S6czlKhjMiQ2xTGxKntIKorx7lRnKtCI4sR0hinOkKbGN1JZ40wCtkLjnsBtpGSx6IF2-PBcPyxcfciwZNVLqMoytq7lm5-UXaaDQT0hQL-hIMzeLgZq3kG_PpX_-dtuwZXasrNuisduQ5btrwBP4ZWlaxP8XtsQAFUalrfSGWVY8iKWRcRCLcLm2feR0HtYO8UBeCXE9adTnBly6MZQ9LPcKSeT8WBu8d6Tf709UhjUk__oY8swr_4SA321lLVFIOkn-1V0-X3mSpLNvThrXZxEz6cy67cglZZlfYOMI76LVXaNqZdYJdEazqN5SpKUrS_nSiA52sRyk2dy51Kikxz9OlI2vJG2gJ43HQ9WSUw-VunPZLDpgPlHPcfqvkkr01YLtH5TbnQUqgijiOprYsdYoJLlRQ61QE8IynOyTLiZIyqL3jgkijHWN6VIkM6jugawM5aWPPaZC7y35IawKOmGY0dnWCp0lanvg-PUsmTNIDbK71o5hyTe88TGYDc0JiNRW22lMdHPqE6J9KadZK7_57XQ7iEupO_GYwO7sFlQYWgKXw_2YHWcn5q78NF82V5vJg_qC0Bg0_nrUW_ACvwp98
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Mean+Field+Initialization+of+the+Annealed+Importance+Sampling+Algorithm+for+an+Efficient+Evaluation+of+the+Partition+Function+Using+Restricted+Boltzmann+Machines&rft.jtitle=Entropy+%28Basel%2C+Switzerland%29&rft.au=Prat+Pou%2C+Arnau&rft.au=Romero%2C+Enrique&rft.au=Mart%C3%AD%2C+Jordi&rft.au=Mazzanti%2C+Ferran&rft.date=2025-02-06&rft.eissn=1099-4300&rft.volume=27&rft.issue=2&rft_id=info:doi/10.3390%2Fe27020171&rft_id=info%3Apmid%2F40003168&rft.externalDocID=40003168
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1099-4300&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1099-4300&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1099-4300&client=summon