A modified Consensus-Based Optimization model: consensus formation and uniform-in-time propagation of chaos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Young-Pil, Lee, Seungchan, Song, Sihyun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914168870797312
author Choi, Young-Pil
Lee, Seungchan
Song, Sihyun
author_facet Choi, Young-Pil
Lee, Seungchan
Song, Sihyun
contents We introduce a modified Consensus-Based Optimization model that admits a fully unified and rigorous analysis of its finite-particle dynamics, the associated McKean--Vlasov equation, and their optimization behavior under a single set of structural framework. The key ingredient is a regularized Gibbs weight that stabilizes the consensus point and avoids degeneracies present in the classical formulation, eliminating the need for cutoffs, rescaling, or boundedness assumptions on the objective function. Our first main result establishes large-time consensus for the particle system: when the drift exceeds an explicit threshold, all particles converge exponentially to a common random limit that concentrates near the global minimizer. Our second result proves uniform-in-time propagation of chaos, providing quantitative and dimension-free convergence of the empirical measure to the McKean--Vlasov dynamics. Finally, we show that the mean-field system reaches deterministic consensus and that its consensus point approaches the global minimizer in the regime of highly concentrated Gibbs weights. Together, these results yield a unified and internally consistent theoretical framework for consensus-based optimization under substantially relaxed regularity assumptions on the objective function.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19116
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A modified Consensus-Based Optimization model: consensus formation and uniform-in-time propagation of chaos
Choi, Young-Pil
Lee, Seungchan
Song, Sihyun
Probability
Analysis of PDEs
Optimization and Control
35Q93, 70F10, 35B40, 37N40
We introduce a modified Consensus-Based Optimization model that admits a fully unified and rigorous analysis of its finite-particle dynamics, the associated McKean--Vlasov equation, and their optimization behavior under a single set of structural framework. The key ingredient is a regularized Gibbs weight that stabilizes the consensus point and avoids degeneracies present in the classical formulation, eliminating the need for cutoffs, rescaling, or boundedness assumptions on the objective function. Our first main result establishes large-time consensus for the particle system: when the drift exceeds an explicit threshold, all particles converge exponentially to a common random limit that concentrates near the global minimizer. Our second result proves uniform-in-time propagation of chaos, providing quantitative and dimension-free convergence of the empirical measure to the McKean--Vlasov dynamics. Finally, we show that the mean-field system reaches deterministic consensus and that its consensus point approaches the global minimizer in the regime of highly concentrated Gibbs weights. Together, these results yield a unified and internally consistent theoretical framework for consensus-based optimization under substantially relaxed regularity assumptions on the objective function.
title A modified Consensus-Based Optimization model: consensus formation and uniform-in-time propagation of chaos
topic Probability
Analysis of PDEs
Optimization and Control
35Q93, 70F10, 35B40, 37N40
url https://arxiv.org/abs/2511.19116