2 papers
eess.SY2025
Decentralized Optimization with Amplified Privacy via Efficient Communication
Wei Huo, Changxin Liu, Kemi Ding +2
Decentralized optimization is crucial for multi-agent systems, with significant concerns about communication efficiency and privacy. This paper explores the role of efficient commu…
cs.LG2025
Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy
Wei Huo, Changxin Liu, Kemi Ding +2
This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated le…