Uniform-in-time weak propagation of chaos for consensus-based optimization
This provides theoretical guarantees for the convergence of CBO particle systems to the global minimizer, which is incremental for optimization algorithms in machine learning and related fields.
The paper tackles the problem of analyzing the uniform-in-time weak propagation of chaos for the consensus-based optimization (CBO) method on a bounded domain, showing that the weak error scales as O(N^{-1}) uniformly in time, where N is the number of particles.
We study the uniform-in-time weak propagation of chaos for the consensus-based optimization (CBO) method on a bounded searching domain. We apply the methodology for studying long-time behaviors of interacting particle systems developed in the work of Delarue and Tse (ArXiv:2104.14973). Our work shows that the weak error has order $O(N^{-1})$ uniformly in time, where $N$ denotes the number of particles. The main strategy behind the proofs are the decomposition of the weak errors using the linearized Fokker-Planck equations and the exponential decay of their Sobolev norms. Consequently, our result leads to the joint convergence of the empirical distribution of the CBO particle system to the Dirac-delta distribution at the global minimizer in population size and running time in Wasserstein-type metrics.