关于计算结构化非光滑非凸规划的戈德斯坦近似二阶驻点
On computing Goldstein approximate second-order stationary points of structured nonsmooth nonconvex programs
浏览论文内容
中文总结 AI 辅助
研究如何计算结构化非光滑非凸规划的戈德斯坦近似二阶驻点,采用随机一阶算法,利用随机平滑工具,给出算法神谕复杂度,还扩展到弱凸函数并应用于双层优化。
中文摘要 AI 辅助
本文展示了一种随机一阶算法,利用随机平滑工具来计算\(L\)-光滑函数的戈德斯坦近似二阶驻点。该算法的神谕复杂度为\(\widetilde{O}({ n^2}/{\varepsilon^9}+{ n^3}/{\varepsilon^7})\),其中\(n\)为输入维度,\(\varepsilon\)为公差。还给出了对弱凸函数的扩展及在双层优化中的应用。
英文摘要
In this paper, we exhibit a randomized first-order algorithm to compute Goldstein approximate second-order stationary points of $L$-smooth functions, using tools from randomized smoothing. The algorithm has oracle complexity $\widetilde{O}({ n^2}/{\varepsilon^9}+{ n^3}/{\varepsilon^7})$, where $n=1,2,\ldots$ is the input dimension and $\varepsilon>0$ is the (common) tolerance. We also present extensions to weakly convex functions and applications to bilevel optimization.