Sampling can be faster than optimization

Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical understanding of the relationships between these 2 kinds of methodology...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the National Academy of Sciences - PNAS Ročník 116; číslo 42; s. 20881
Hlavní autoři: Ma, Yi-An, Chen, Yuansi, Jin, Chi, Flammarion, Nicolas, Jordan, Michael I
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 15.10.2019
Témata:
ISSN:1091-6490, 1091-6490
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical understanding of the relationships between these 2 kinds of methodology, and limited understanding of relative strengths and weaknesses. Moreover, existing results have been obtained primarily in the setting of convex functions (for optimization) and log-concave functions (for sampling). In this setting, where local properties determine global properties, optimization algorithms are unsurprisingly more efficient computationally than sampling algorithms. We instead examine a class of nonconvex objective functions that arise in mixture modeling and multistable systems. In this nonconvex setting, we find that the computational complexity of sampling algorithms scales linearly with the model dimension while that of optimization algorithms scales exponentially.
AbstractList Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical understanding of the relationships between these 2 kinds of methodology, and limited understanding of relative strengths and weaknesses. Moreover, existing results have been obtained primarily in the setting of convex functions (for optimization) and log-concave functions (for sampling). In this setting, where local properties determine global properties, optimization algorithms are unsurprisingly more efficient computationally than sampling algorithms. We instead examine a class of nonconvex objective functions that arise in mixture modeling and multistable systems. In this nonconvex setting, we find that the computational complexity of sampling algorithms scales linearly with the model dimension while that of optimization algorithms scales exponentially.Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical understanding of the relationships between these 2 kinds of methodology, and limited understanding of relative strengths and weaknesses. Moreover, existing results have been obtained primarily in the setting of convex functions (for optimization) and log-concave functions (for sampling). In this setting, where local properties determine global properties, optimization algorithms are unsurprisingly more efficient computationally than sampling algorithms. We instead examine a class of nonconvex objective functions that arise in mixture modeling and multistable systems. In this nonconvex setting, we find that the computational complexity of sampling algorithms scales linearly with the model dimension while that of optimization algorithms scales exponentially.
Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical understanding of the relationships between these 2 kinds of methodology, and limited understanding of relative strengths and weaknesses. Moreover, existing results have been obtained primarily in the setting of convex functions (for optimization) and log-concave functions (for sampling). In this setting, where local properties determine global properties, optimization algorithms are unsurprisingly more efficient computationally than sampling algorithms. We instead examine a class of nonconvex objective functions that arise in mixture modeling and multistable systems. In this nonconvex setting, we find that the computational complexity of sampling algorithms scales linearly with the model dimension while that of optimization algorithms scales exponentially.
Author Chen, Yuansi
Jordan, Michael I
Ma, Yi-An
Jin, Chi
Flammarion, Nicolas
Author_xml – sequence: 1
  givenname: Yi-An
  orcidid: 0000-0001-6074-6638
  surname: Ma
  fullname: Ma, Yi-An
  organization: Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720
– sequence: 2
  givenname: Yuansi
  orcidid: 0000-0002-8899-7380
  surname: Chen
  fullname: Chen, Yuansi
  organization: Department of Statistics, University of California, Berkeley, CA 94720
– sequence: 3
  givenname: Chi
  surname: Jin
  fullname: Jin, Chi
  organization: Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720
– sequence: 4
  givenname: Nicolas
  surname: Flammarion
  fullname: Flammarion, Nicolas
  organization: Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720
– sequence: 5
  givenname: Michael I
  orcidid: 0000-0001-8935-817X
  surname: Jordan
  fullname: Jordan, Michael I
  email: jordan@cs.berkeley.edu
  organization: Department of Statistics, University of California, Berkeley, CA 94720
BackLink https://www.ncbi.nlm.nih.gov/pubmed/31570618$$D View this record in MEDLINE/PubMed
BookMark eNpNjztLxEAUhQdZcR9a20nKbbLOnUlyc0tZfMGChVqHeWokmcRMUuivN-AKVuc78HHgrNkidMExdgl8BxzldR9U3EEpOOcSoDhhK-AEaZERX_zjJVvH-DFLlJf8jC0l5MgLKFds-6zavqnDW2JUSLRLvIqjG5Lxfa5dP9Zt_a3Gugvn7NSrJrqLY27Y693ty_4hPTzdP-5vDqnJkMZUKAOQWa08odSWa10q5OAJygKkzclqRGfIZZnODXpHYGyZofLS-wJJbNj2d7cfus_JxbFq62hc06jguilWQhBhgSjErF4d1Um3zlb9ULdq-Kr-3okfs69S1g
CitedBy_id crossref_primary_10_1016_j_physd_2021_132844
crossref_primary_10_3390_math10060898
crossref_primary_10_1007_s10107_023_01988_8
crossref_primary_10_1109_TIT_2024_3522494
crossref_primary_10_1016_j_jcp_2025_114208
crossref_primary_10_1109_LRA_2024_3455782
crossref_primary_10_1016_j_automatica_2023_111221
crossref_primary_10_1007_s11222_021_10054_2
crossref_primary_10_1109_TETCI_2021_3083428
crossref_primary_10_1214_25_EJS2397
crossref_primary_10_1214_22_BA1331
crossref_primary_10_1007_s11222_023_10220_8
crossref_primary_10_1038_s41598_025_12998_1
crossref_primary_10_3390_hydrology11020014
crossref_primary_10_1016_j_asr_2021_10_008
crossref_primary_10_1016_j_compstruct_2023_117657
crossref_primary_10_3390_e25081234
crossref_primary_10_1109_TIT_2023_3318152
crossref_primary_10_1088_1742_5468_ad01b2
crossref_primary_10_1017_jpr_2025_10025
crossref_primary_10_1093_imanum_draf045
crossref_primary_10_1109_TRPMS_2022_3148373
crossref_primary_10_1186_s12874_024_02235_0
crossref_primary_10_1137_24M1633765
crossref_primary_10_1088_1361_6420_ac9582
crossref_primary_10_1080_24725854_2023_2184884
crossref_primary_10_1109_TWC_2023_3342618
crossref_primary_10_1190_geo2021_0776_1
crossref_primary_10_1038_s42005_021_00768_0
crossref_primary_10_1109_TSP_2024_3516502
crossref_primary_10_1214_22_BJPS538
crossref_primary_10_1038_s41598_021_90144_3
crossref_primary_10_1007_s00180_023_01411_y
crossref_primary_10_1007_s40304_023_00350_w
crossref_primary_10_1109_TCOMM_2024_3435340
crossref_primary_10_1109_TASE_2024_3475951
crossref_primary_10_3150_21_BEJ1343
crossref_primary_10_3390_axioms11090462
crossref_primary_10_1109_JPROC_2024_3437730
crossref_primary_10_1109_TAES_2023_3320634
crossref_primary_10_1371_journal_pcbi_1010340
crossref_primary_10_1214_23_AAP2021
crossref_primary_10_1016_j_spa_2025_104684
crossref_primary_10_1177_17456916241258951
crossref_primary_10_1109_TRO_2025_3551198
crossref_primary_10_1016_j_tws_2022_110096
crossref_primary_10_1093_jrsssb_qkaf009
ContentType Journal Article
Copyright Copyright © 2019 the Author(s). Published by PNAS.
Copyright_xml – notice: Copyright © 2019 the Author(s). Published by PNAS.
DBID NPM
7X8
DOI 10.1073/pnas.1820003116
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Sciences (General)
EISSN 1091-6490
ExternalDocumentID 31570618
Genre Journal Article
GroupedDBID ---
-DZ
-~X
.55
0R~
123
29P
2AX
2FS
2WC
4.4
53G
5RE
5VS
85S
AACGO
AAFWJ
AANCE
ABBHK
ABOCM
ABPLY
ABPPZ
ABTLG
ABXSQ
ABZEH
ACGOD
ACHIC
ACIWK
ACNCT
ACPRK
ADQXQ
ADULT
AENEX
AEUPB
AEXZC
AFFNX
AFOSN
AFRAH
ALMA_UNASSIGNED_HOLDINGS
AQVQM
BKOMP
CS3
D0L
DCCCD
DIK
DU5
E3Z
EBS
EJD
F5P
FRP
GX1
H13
HH5
HYE
IPSME
JAAYA
JBMMH
JENOY
JHFFW
JKQEH
JLS
JLXEF
JPM
JSG
JST
KQ8
L7B
LU7
N9A
NPM
N~3
O9-
OK1
PNE
PQQKQ
R.V
RHI
RNA
RNS
RPM
RXW
SA0
SJN
TAE
TN5
UKR
W8F
WH7
WOQ
WOW
X7M
XSW
Y6R
YBH
YKV
YSK
ZCA
~02
~KM
7X8
ID FETCH-LOGICAL-c479t-2ac114dbaf973bd0bb8a701f918613d59db77ec9e44b5c7fe91cd847af3ff6792
IEDL.DBID 7X8
ISICitedReferencesCount 96
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000490183000018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1091-6490
IngestDate Thu Sep 04 16:31:01 EDT 2025
Thu Apr 03 06:56:30 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 42
Keywords Langevin Monte Carlo
nonconvex optimization
computational complexity
Language English
License Copyright © 2019 the Author(s). Published by PNAS.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c479t-2ac114dbaf973bd0bb8a701f918613d59db77ec9e44b5c7fe91cd847af3ff6792
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-8899-7380
0000-0001-6074-6638
0000-0001-8935-817X
OpenAccessLink https://www.pnas.org/doi/10.1073/pnas.1820003116
PMID 31570618
PQID 2299767722
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2299767722
pubmed_primary_31570618
PublicationCentury 2000
PublicationDate 2019-10-15
PublicationDateYYYYMMDD 2019-10-15
PublicationDate_xml – month: 10
  year: 2019
  text: 2019-10-15
  day: 15
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Proceedings of the National Academy of Sciences - PNAS
PublicationTitleAlternate Proc Natl Acad Sci U S A
PublicationYear 2019
SSID ssj0009580
Score 2.6698806
Snippet Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 20881
Title Sampling can be faster than optimization
URI https://www.ncbi.nlm.nih.gov/pubmed/31570618
https://www.proquest.com/docview/2299767722
Volume 116
WOSCitedRecordID wos000490183000018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEA5qPXhR67O-iOChHmI32exmcxIRiwctBRV6K3mKB3erW_39TnZT9CIIXnILhMlkvi8zyTcInRXKaAPASpROFOGAuERnzBMOZNxpr7nwjWT-nRiNislEjmPCrY7PKhcxsQnUtjIhRz5gEDdFDlyQXc7eSOgaFaqrsYXGMuqkQGWCV4tJ8UN0t2jVCCQlOZfJQtpHpINZqeqLIF4evJrmv_PLBmeGG_9d4SZajwwTX7Uu0UVLrtxC3XiGa9yPQtPn26j_oMJ78vIZg32xdtirIJuAQzYdVxBLXuMnzR30NLx5vL4lsXMCMVzIOWHKwD3HauWlSLVNtC6USKiXtAD4tpm0WghnpONcZ0Z4J6mxgFPKp97nQrJdtFJWpdtHmNlcC-sTp1ioUDIN_EtnObfUZUmqbA-dLqwxBc8M5QZVuuqjnn7bo4f2WpNOZ62ExjSlmQAmURz8YfYhWgOWIgNg0OwIdTycS3eMVs3n_KV-P2m2HMbR-P4LYxC1qQ
linkProvider ProQuest
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=Sampling+can+be+faster+than+optimization&rft.jtitle=Proceedings+of+the+National+Academy+of+Sciences+-+PNAS&rft.au=Ma%2C+Yi-An&rft.au=Chen%2C+Yuansi&rft.au=Jin%2C+Chi&rft.au=Flammarion%2C+Nicolas&rft.date=2019-10-15&rft.issn=1091-6490&rft.eissn=1091-6490&rft.volume=116&rft.issue=42&rft.spage=20881&rft_id=info:doi/10.1073%2Fpnas.1820003116&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1091-6490&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1091-6490&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1091-6490&client=summon