Consensus-based optimization methods converge globally

M Fornasier, T Klock, K Riedl - SIAM Journal on Optimization, 2024 - SIAM
In this paper we study consensus-based optimization (CBO), which is a multiagent
metaheuristic derivative-free optimization method that can globally minimize nonconvex …

CBO: Consensus-Based Bi-Level Optimization

NG Trillos, S Li, K Riedl, Y Zhu - arxiv preprint arxiv:2411.13394, 2024 - arxiv.org
Bi-level optimization problems, where one wishes to find the global minimizer of an upper-
level objective function over the globally optimal solution set of a lower-level objective, arise …

Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization

NG Trillos, AK Akash, S Li, K Riedl, Y Zhu - arxiv preprint arxiv …, 2024 - arxiv.org
Adversarial attacks pose significant challenges in many machine learning applications,
particularly in the setting of distributed training and federated learning, where malicious …