arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.03210math.OC
收藏

非凸约束优化的自适应方向分解方法

Adaptive directional decomposition methods for nonconvex constrained optimization

School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院)

Qiankun Shi, Xiao Wang

AI总结:

本文针对带等式和不等式约束的非凸优化问题,提出基于分解策略与自适应参数更新的一阶算法框架,并在确定性与随机情形下分别建立了达到或优于现有水平的迭代复杂度和oracle复杂度界。

摘要:

本文研究同时带有等式约束和不等式约束的非凸约束优化问题,涵盖确定性情形与随机情形。我们提出一种新的一阶算法框架,该框架采用分解策略来平衡目标函数下降与约束满足,并自适应更新步长和评价参数。在特定条件下,所提出的自适应方向分解方法在确定性情形下找到ε-KKT点的迭代复杂度达到O(ε^{-2})量级。在随机情形下,我们进一步提出随机化变体方法,并借助扰动理论分析其理论性质。我们建立了高概率oracle复杂度:在不存在(相应地,存在)逐样本光滑性时,为找到ε-KKT点,梯度和约束评估的复杂度分别为\ ilde O(ε^{-4}, ε^{-6})(相应地,\ ilde O(ε^{-3}, ε^{-5}))量级。据我们所知,所获得的复杂度界与文献中最先进的结果相当或有所改进。

英文摘要:

In this paper, we study nonconvex constrained optimization problems with both equality and inequality constraints, covering deterministic and stochastic settings. We propose a novel first-order algorithm framework that employs a decomposition strategy to balance objective reduction and constraint satisfaction, together with adaptive update of stepsizes and merit parameters. Under certain conditions, the proposed adaptive directional decomposition methods attain an iteration complexity of order \(O(ε^{-2})\) for finding an \(ε\)-KKT point in the deterministic setting. In the stochastic setting, we further develop stochastic variants of approaches and analyze their theoretical properties by leveraging the perturbation theory. We establish the high-probability oracle complexity to find an $ε$-KKT point of order \( \tilde O(ε^{-4}, ε^{-6}) \) (resp. \(\tilde O(ε^{-3}, ε^{-5}) \)) for gradient and constraint evaluations, in the absence (resp. presence) of sample-wise smoothness. To the best of our knowledge, the obtained complexity bounds are comparable to, or improve upon, the state-of-the-art results in the literature.

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。

↑