2 papers
cs.LG2025
Second-Order Convergence in Private Stochastic Non-Convex Optimization
Youming Tao, Zuyuan Zhang, Dongxiao Yu +3
We investigate the problem of finding second-order stationary points (SOSP) in differentially private (DP) stochastic non-convex optimization. Existing methods suffer from two key…
cs.LG2024
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee
Mengtong Gao, Yifei Zou, Zuyuan Zhang +2
The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates…