Federated Primal Dual Fixed Point Algorithm
Ya‐Nan Zhu, Jingwei Liang, Xiaoqun Zhang · SIAM Journal on Mathematics of Data Science · 2024
Abstract. Federated learning is a distributed learning paradigm that allows several clients to learn a global model without sharing their private data. In this paper, we generalize a primal dual fixed point (PDFP) method [P. Chen, J. Huang, and X. Zhang, Inverse Problems, 29 (2013), 025011] to the federated learning setting and propose an algorithm called federated PDFP (FPDFP) for solving composite optimization problems. In addition, a quantization scheme is applied to reduce the communication overhead during the learning process. An [Formula: see text] convergence rate (where [Formula: see text] is the communication round) of the proposed FPDFP is provided. Numerical experiments, including graph-guided logistic regression and three-dimensional computed tomography reconstruction, are considered to evaluate the proposed algorithm.