We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy. Most prior work on this problem is restricted to the case where the loss function is Lipschitz. Instead, as introduced by Wang, Xiao, Devadas, and Xu, we study general convex loss functions with the assumption that the distribution of gradients has bounded $k$-th moments. We provide improved upper bounds on the excess population risk under approximate differential privacy of $\tilde{O}\left(\sqrt{\frac{d}{n}}+\left(\frac{d}{\epsilon n}\right)^{\frac{k-1}{k}}\right)$ and $\tilde{O}\left(\frac{d}{n}+\left(\frac{d}{\epsilon n}\right)^{\frac{2k-2}{k}}\right)$ for convex and strongly convex loss functions, respectively. We also prove nearly-matching lower bounds under the constraint of pure differential privacy, giving strong evidence that our bounds are tight.

本文研究带有重尾数据的随机凸优化问题，并在差分隐私（DP）约束条件下进行研究。该文提出了一种新的算法用于估计重尾数据的均值，并针对凸损失函数提供了改进的上界。同时，证明了私密随机凸优化的几乎匹配下界，这表明了纯DP和集中DP之间的新分离。

重尾数据的差分隐私随机凸优化的改进速率