Optimization of the Sherrington-Kirkpatrick Hamiltonian

Let A be a symmetric random matrix with independent and identically distributed Gaussian entries above the diagonal. We consider the problem of maximizing the quadratic form associated to A over binary vectors. In the language of statistical physics, this amounts to finding the ground state of the S...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / annual Symposium on Foundations of Computer Science pp. 1417 - 1433
Main Author: Montanari, Andrea
Format: Conference Proceeding
Language:English
Published: IEEE 01.11.2019
Subjects:
Approximation algorithms
Complexity theory
Glass
Message passing
message passing algorithms
Optimization
Physics
replica symmetry breaking
Sherrington-Kirkpatrick
Signal processing algorithms
spin glasses
ISSN:2575-8454
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Let A be a symmetric random matrix with independent and identically distributed Gaussian entries above the diagonal. We consider the problem of maximizing the quadratic form associated to A over binary vectors. In the language of statistical physics, this amounts to finding the ground state of the Sherrington-Kirkpatrick model of spin glasses. The asymptotic value of this optimization problem was characterized by Parisi via a celebrated variational principle, subsequently proved by Talagrand. We give an algorithm that, for any ε > 0, outputs a feasible solution whose value is at least (1 - ε) of the optimum, with probability converging to one as the dimension n of the matrix diverges. The algorithm's time complexity is of order n 2 . It is a message-passing algorithm, but the specific structure of its update rules is new. As a side result, we prove that, at (low) non-zero temperature, the algorithm constructs approximate solutions of the Thouless-Anderson-Palmer equations.
AbstractList Let A be a symmetric random matrix with independent and identically distributed Gaussian entries above the diagonal. We consider the problem of maximizing the quadratic form associated to A over binary vectors. In the language of statistical physics, this amounts to finding the ground state of the Sherrington-Kirkpatrick model of spin glasses. The asymptotic value of this optimization problem was characterized by Parisi via a celebrated variational principle, subsequently proved by Talagrand. We give an algorithm that, for any ε > 0, outputs a feasible solution whose value is at least (1 - ε) of the optimum, with probability converging to one as the dimension n of the matrix diverges. The algorithm's time complexity is of order n 2 . It is a message-passing algorithm, but the specific structure of its update rules is new. As a side result, we prove that, at (low) non-zero temperature, the algorithm constructs approximate solutions of the Thouless-Anderson-Palmer equations.
Author Montanari, Andrea
Author_xml – sequence: 1
  givenname: Andrea
  surname: Montanari
  fullname: Montanari, Andrea
  organization: Stanford University
BookMark eNotzL1OwzAUQGGDQKIpzAwseYGE67_aHlFEW0SlDIW5urEdato4keMFnh4kmI70DacgV3GMnpB7CjWlYB7XbbOvGVBTA4BWF6SgimkqjGTykiyYVLLSQoobUszzJ4AACWJBVDvlMIRvzGGM5diX-ejL_dGnFOJHHmP1GtJpwpyCPZVbHML5FwPGW3Ld43n2d_9dkvf181uzrXbt5qV52lWBAc8VtUagEqrjVFPQzndWUWlXSB0I1kmmuOI9B8-s82i5c7bDXncOkRnner4kD3_f4L0_TCkMmL4O2gi94sB_ABG-SJk
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/FOCS.2019.00087
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Mathematics
Physics
EISBN 1728149525
9781728149523
EISSN 2575-8454
EndPage 1433
ExternalDocumentID 8948630
Genre orig-research
GroupedDBID --Z
29O
6IE
6IH
6IK
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIO
ID FETCH-LOGICAL-i203t-1c94a747b318108debc715c6a1d042b527373f30e2cdeac3ddcbaf8bdaa29ddf3
IEDL.DBID RIE
ISICitedReferencesCount 63
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000510015300078&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:31:21 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-1c94a747b318108debc715c6a1d042b527373f30e2cdeac3ddcbaf8bdaa29ddf3
PageCount 17
ParticipantIDs ieee_primary_8948630
PublicationCentury 2000
PublicationDate 2019-Nov.
PublicationDateYYYYMMDD 2019-11-01
PublicationDate_xml – month: 11
  year: 2019
  text: 2019-Nov.
PublicationDecade 2010
PublicationTitle Proceedings / annual Symposium on Foundations of Computer Science
PublicationTitleAbbrev SFCS
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0040504
Score 2.4680707
Snippet Let A be a symmetric random matrix with independent and identically distributed Gaussian entries above the diagonal. We consider the problem of maximizing the...
SourceID ieee
SourceType Publisher
StartPage 1417
SubjectTerms Approximation algorithms
Complexity theory
Glass
Message passing
message passing algorithms
Optimization
Physics
replica symmetry breaking
Sherrington-Kirkpatrick
Signal processing algorithms
spin glasses
Title Optimization of the Sherrington-Kirkpatrick Hamiltonian
URI https://ieeexplore.ieee.org/document/8948630
WOSCitedRecordID wos000510015300078&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5qUdCL2lbqkz14NHZ3k26Sc7EUxLagQm8lTyjFtvTh73eSXSuCF28hBAKTzCuZ7xuAe-cVR0_niew6RhjDBAXjZE5y6b1zQnOqWWw2wYdDMZnIcQ0e9lgY51wsPnOPYRj_8u3S7MJTWUdIJgqKCfoB50WJ1fq2uhh3pKyi7slS2emPeq-hcCuwUabid--U6Dr6p__b9AxaPxi8ZLz3LudQc4sGnLzsWVY3DTiK5Ztm0wQ-Qs3_qCCVydInuCopWRdjgTx5nq3nq8jGP08G4U0DJ_FitOC9__TWG5CqJQKZ5SndksxIpjAD0KiKWSqs04ZnXVOozKL26cCmxqmnqcuNRZNKrTVaeaGtUrm01tMLqC-WC9eGhHelKxTLvcQoytpMCcq4zbhQpigwaryEZhDGdFWyXkwrOVz9PX0Nx0HaJUrvBurb9c7dwqH53M4267t4VF_3OZZh
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5KVdSL2iq-3YNH1-5uspvkXCyVPsEKvZVsHlCKbenD3-8ku1YEL95CCAlMMpmZZL5vAB6NlQwtnQ1FamhIKQYo6CezMBHWGsNzRnLqi02wfp-Px2JYgacdFsYY45PPzLNr-r98vVBb91TW4ILyjGCAvpe6WQu01ve9i55HREvynjgSjdag-eZStxwfZcR_V0_xxqN18r9lT-H8B4UXDHf25QwqZl6D496OZ3VdgwOfwKnWdWAD1P2PElQZLGyAo4KCd9GnyIed6Wq29Hz8s6DtXjWwE4_GOby3XkbNdlgWRQinSUQ2YawElRgD5KiMccS1yRWLU5XJWKP-5Y5PjRFLIpMojZcq0Vrl0vJcS5kIrS25gOp8MTeXELBUmEzSxAr0o7SOJSeU6ZhxqbIM_cYrqDthTJYF78WklMP1390PcNge9bqT7mu_cwNHTvIFZu8WqpvV1tzBvvrcTNere79tX_lYmag
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=proceeding&rft.title=Proceedings+%2F+annual+Symposium+on+Foundations+of+Computer+Science&rft.atitle=Optimization+of+the+Sherrington-Kirkpatrick+Hamiltonian&rft.au=Montanari%2C+Andrea&rft.date=2019-11-01&rft.pub=IEEE&rft.eissn=2575-8454&rft.spage=1417&rft.epage=1433&rft_id=info:doi/10.1109%2FFOCS.2019.00087&rft.externalDocID=8948630