Mean-field limits for Consensus-Based Optimization and Sampling
arXiv:2312.07373 · doi:10.1051/cocv/2025060
Abstract
For algorithms based on interacting particle systems that admit a mean-field description, convergence analysis is often more accessible at the mean-field level. In order to transfer convergence results obtained at the mean-field level to the finite ensemble size setting, it is desirable to show that the particle dynamics converge in an appropriate sense to the corresponding mean-field dynamics. In this paper, we prove quantitative mean-field limit results for two related interacting particle systems: Consensus-Based Optimization and Consensus-Based Sampling. Our approach requires a generalization of Sznitman's classical argument: in order to circumvent issues related to the lack of global Lipschitz continuity of the coefficients, we discard an event of small probability, the contribution of which is controlled using moment estimates for the particle systems. In addition, we present new results on the well-posedness of the particle systems and their mean-field limit, and provide novel stability estimates for the weighted mean and the weighted covariance.
References in corpus (9)
- On the Random Batch Method for second order interacting particle systems
- Propagation of chaos: a review of models, methods and applications. II. Applications
- On the Global Convergence of Particle Swarm Optimization Methods
- On the mean-field limit for the consensus-based optimization
- Consensus-Based Optimization Methods Converge Globally
- Consensus based optimization via jump-diffusion stochastic differential equations
- Convergence of Anisotropic Consensus-Based Optimization in Mean-Field Law
- Polarized consensus-based dynamics for optimization and sampling
- CBX: Python and Julia packages for consensus-based interacting particle methods