2 papers
cs.LG2023
On the Tradeoff between Privacy Preservation and Byzantine-Robustness in Decentralized Learning
Haoxiang Ye, Heng Zhu, Qing Ling
This paper jointly considers privacy preservation and Byzantine-robustness in decentralized learning. In a decentralized network, honest-but-curious agents faithfully follow the pr…
cs.LG2023
Byzantine-Robust Distributed Online Learning: Taming Adversarial Participants in An Adversarial Environment
Xingrong Dong, Zhaoxian Wu, Qing Ling +1
This paper studies distributed online learning under Byzantine attacks. The performance of an online learning algorithm is often characterized by (adversarial) regret, which evalua…