Journal article
Consensus-based optimization for saddle point problems
- Abstract:
- In this paper, we propose consensus-based optimization for saddle point problems (CBO-SP), a novel multi-particle metaheuristic derivative-free optimization method capable of provably finding global Nash equilibria. Following the idea of swarm intelligence, the method employs two groups of interacting particles, one which performs a minimization over one variable while the other performs a maximization over the other variable. The two groups constantly exchange information through a suitably weighted average. This paradigm permits a passage to the mean-field limit, which makes the method amenable to theoretical analysis, and it allows to obtain rigorous convergence guarantees under reasonable assumptions about the initialization and the objective function, which most notably include nonconvex-nonconcave objectives. We further provide numerical evidence for the success of the algorithm.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 8.5MB, Terms of use)
-
- Publisher copy:
- 10.1137/22m1543367
Authors
- Publisher:
- Society for Industrial and Applied Mathematics
- Journal:
- SIAM Journal on Control and Optimization More from this journal
- Volume:
- 62
- Issue:
- 2
- Pages:
- 1093-1121
- Publication date:
- 2024-03-25
- Acceptance date:
- 2023-09-22
- DOI:
- EISSN:
-
1095-7138
- ISSN:
-
0363-0129
- Language:
-
English
- Keywords:
- Pubs id:
-
2036350
- Local pid:
-
pubs:2036350
- Deposit date:
-
2024-10-05
- ARK identifier:
Terms of use
- Copyright holder:
- Society for Industrial and Applied Mathematics
- Copyright date:
- 2024
- Rights statement:
- © 2024 Society for Industrial and Applied Mathematics.
- Notes:
- This is the accepted manuscript version of the article. The final version is available online from Society for Industrial and Applied Mathematics at https://dx.doi.org/10.1137/22m1543367
If you are the owner of this record, you can report an update to it here: Report update to this record