Privacy-preserving Stochastic Gradual Learning
IEEE Transactions on Knowledge and Data Engineering(2021)
摘要
It is challenging for stochastic optimization to handle large-scale sensitive data safely. Duchi et al. recently proposed a private sampling strategy to solve privacy leakage in stochastic optimization. However, this strategy leads to a degeneration in robustness, since this strategy is equal to noise injection on each gradient, which adversely affects updates of the primal variable. To address th...
更多查看译文
关键词
Privacy,Optimization,Differential privacy,Robustness,Stochastic processes,Task analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络