Demonstrating real advantage of machine learning–enhanced Monte Carlo for combinatorial optimization.
Saved in:
| Title: | Demonstrating real advantage of machine learning–enhanced Monte Carlo for combinatorial optimization. |
|---|---|
| Authors: | Del Bono, Luca Maria1,2, Ricci-Tersenghi, Federico1,2,3 federico.ricci@uniroma1.it, Zamponi, Francesco1 francesco.zamponi@uniroma1.it |
| Source: | Proceedings of the National Academy of Sciences of the United States of America. 5/12/2026, Vol. 123 Issue 19, p1-10. 10p. |
| Subjects: | Combinatorial optimization, Monte Carlo method, Machine learning, Simulated annealing |
| Abstract: | Combinatorial optimization problems are central to both practical applications and the development of optimization methods. While classical and quantum algorithms have been refined over decades, machine learning–assisted approaches are comparatively recent and have not yet consistently outperformed simple, state-of-the-art classical methods. Here, we focus on a class of Quadratic Unconstrained Binary Optimization problems, specifically the challenge of finding minimum energy configurations in three-dimensional Ising spin glasses. We use a Global Annealing Monte Carlo algorithm that integrates standard local moves with global moves proposed via machine learning. We show that local moves play a crucial role in achieving optimal performance. Benchmarking against Simulated Annealing and Population Annealing, we demonstrate that Global Annealing not only surpasses the performance of Simulated Annealing but also exhibits greater robustness than Population Annealing, maintaining effectiveness across problem hardness and system size without hyperparameter tuning. These results provide clear and robust evidence that a machine learning–assisted optimization method can exceed the capabilities of classical state-of-the-art techniques in a combinatorial optimization setting. [ABSTRACT FROM AUTHOR] |
| Copyright of Proceedings of the National Academy of Sciences of the United States of America is the property of National Academy of Sciences and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 193988585 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Demonstrating real advantage of machine learning–enhanced Monte Carlo for combinatorial optimization. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Del+Bono%2C+Luca+Maria%22">Del Bono, Luca Maria</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Ricci-Tersenghi%2C+Federico%22">Ricci-Tersenghi, Federico</searchLink><relatesTo>1,2,3</relatesTo><i> federico.ricci@uniroma1.it</i><br /><searchLink fieldCode="AR" term="%22Zamponi%2C+Francesco%22">Zamponi, Francesco</searchLink><relatesTo>1</relatesTo><i> francesco.zamponi@uniroma1.it</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Proceedings+of+the+National+Academy+of+Sciences+of+the+United+States+of+America%22">Proceedings of the National Academy of Sciences of the United States of America</searchLink>. 5/12/2026, Vol. 123 Issue 19, p1-10. 10p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Combinatorial+optimization%22">Combinatorial optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Monte+Carlo+method%22">Monte Carlo method</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Simulated+annealing%22">Simulated annealing</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Combinatorial optimization problems are central to both practical applications and the development of optimization methods. While classical and quantum algorithms have been refined over decades, machine learning–assisted approaches are comparatively recent and have not yet consistently outperformed simple, state-of-the-art classical methods. Here, we focus on a class of Quadratic Unconstrained Binary Optimization problems, specifically the challenge of finding minimum energy configurations in three-dimensional Ising spin glasses. We use a Global Annealing Monte Carlo algorithm that integrates standard local moves with global moves proposed via machine learning. We show that local moves play a crucial role in achieving optimal performance. Benchmarking against Simulated Annealing and Population Annealing, we demonstrate that Global Annealing not only surpasses the performance of Simulated Annealing but also exhibits greater robustness than Population Annealing, maintaining effectiveness across problem hardness and system size without hyperparameter tuning. These results provide clear and robust evidence that a machine learning–assisted optimization method can exceed the capabilities of classical state-of-the-art techniques in a combinatorial optimization setting. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Proceedings of the National Academy of Sciences of the United States of America is the property of National Academy of Sciences and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193988585 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1073/pnas.2534768123 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 10 StartPage: 1 Subjects: – SubjectFull: Combinatorial optimization Type: general – SubjectFull: Monte Carlo method Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Simulated annealing Type: general Titles: – TitleFull: Demonstrating real advantage of machine learning–enhanced Monte Carlo for combinatorial optimization. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Del Bono, Luca Maria – PersonEntity: Name: NameFull: Ricci-Tersenghi, Federico – PersonEntity: Name: NameFull: Zamponi, Francesco IsPartOfRelationships: – BibEntity: Dates: – D: 12 M: 05 Text: 5/12/2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 00278424 Numbering: – Type: volume Value: 123 – Type: issue Value: 19 Titles: – TitleFull: Proceedings of the National Academy of Sciences of the United States of America Type: main |
| ResultId | 1 |
