arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15352cs.LGcs.CRcs.DSstat.ML
收藏

私人非光滑经验风险最小化与次二次阶随机凸优化

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps

Microsoft Research (MSR) Redmond(微软研究院(雷德蒙德));University of Washington(华盛顿大学);Shanghai Qi Zhi Institute(上海期智研究院)

Janardhan Kulkarni, Yin Tat Lee, Daogao Liu

摘要:

研究了非光滑凸函数的微分私人经验风险最小化和随机凸优化问题。在次二次梯度复杂度下,得到了超额经验风险和超额人口损失的(近)最优界。更确切地说,我们的差分私有算法需要$O(\frac{N^{3/2}}{d^{1/8}}+ \frac{N^2}{d})$梯度查询以获得最佳超额经验风险,这是在子采样和通过卷积平滑函数的帮助下实现的。这是当$d$是超常数时非光滑情况下的第一次二次算法。作为一个直接的应用,使用Feldman等人的迭代局部化方法\cite{fkt20},我们实现了随机凸优化问题的最优超额人口损失,与$O(\min\{N^{5/4}d^{1/8},\frac{ N^{3/2}}{d^{1/8}}\})$梯度查询。我们的工作取得了进展,解决了Basily等人提出的一个问题。\cite{bfgt20},给第一个算法的私人ERM和SCO的次二次步骤。我们注意到,独立的Asi等人。\cite{afkt21}给出了其他算法的私人ERM和SCO次二次步骤。

英文摘要:

We study the differentially private Empirical Risk Minimization (ERM) and Stochastic Convex Optimization (SCO) problems for non-smooth convex functions. We get a (nearly) optimal bound on the excess empirical risk and excess population loss with subquadratic gradient complexity. More precisely, our differentially private algorithm requires $O(\frac{N^{3/2}}{d^{1/8}}+ \frac{N^2}{d})$ gradient queries for optimal excess empirical risk, which is achieved with the help of subsampling and smoothing the function via convolution. This is the first subquadratic algorithm for the non-smooth case when $d$ is super constant. As a direct application, using the iterative localization approach of Feldman et al. \cite{fkt20}, we achieve the optimal excess population loss for stochastic convex optimization problem, with $O(\min\{N^{5/4}d^{1/8},\frac{ N^{3/2}}{d^{1/8}}\})$ gradient queries. Our work makes progress towards resolving a question raised by Bassily et al. \cite{bfgt20}, giving first algorithms for private ERM and SCO with subquadratic steps. We note that independently Asi et al. \cite{afkt21} gave other algorithms for private ERM and SCO with subquadratic steps.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑