2 papers
math.OC2026
Provably Convergent Decentralized Optimization over Directed Graphs under Generalized Smoothness
Yanan Bo, Yongqiang Wang
Decentralized optimization has become a fundamental tool for large-scale learning systems; however, most existing methods rely on the classical Lipschitz smoothness assumption, whi…
cs.CR2025
Setup Once, Secure Always: A Single-Setup Secure Federated Learning Aggregation Protocol with Forward and Backward Secrecy for Dynamic Users
Nazatul Haque Sultan, Yan Bo, Yansong Gao +10
Federated Learning (FL) enables multiple users to collaboratively train a machine learning model without sharing raw data, making it suitable for privacy-sensitive applications. Ho…