AI RESEARCH
Taming the Instability: A Robust Second-Order Optimizer for Federated Learning over Non-IID Data
arXiv CS.LG
•
ArXi:2603.28316v1 Announce Type: new In this paper, we present Federated Robust Curvature Optimization (FedRCO), a novel second-order optimization framework designed to improve convergence speed and reduce communication cost in Federated Learning systems under statistical heterogeneity. Existing second-order optimization methods are often computationally expensive and numerically unstable in distributed settings. In contrast, FedRCO addresses these challenges by integrating an efficient approximate curvature optimizer with a provable stability mechanism.