arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09081math.OCcs.LG
收藏

用于可扩展半定优化的低秩外梯度法

Low-Rank Extragradient Methods for Scalable Semidefinite Optimization

Faculty of Data and Decision Sciences, Technion - Israel Institute of Technology(以色列理工学院数据与决策科学学院)

Dan Garber, Atara Kaplan

AI总结:

本文研究高维半定优化问题,提出在低秩解假设下,初始化于最优解附近的Extragradient方法仅需低秩SVD即可保证标准收敛率,并通过Max-Cut数据集验证了其有效性。

摘要:

我们考虑几类非常重要的半定优化问题,它们包含凸目标函数(平滑或非平滑)以及额外的线性或非线性平滑凸约束,这在统计学、机器学习、组合优化及其他领域无处不在。我们关注高维且合理的设定,即问题存在一个低秩解,且该解满足低秩互补条件。我们提供了几个理论结果,证明在这些情况下,著名的Extragradient方法在初始化于最优原始-对偶解附近时,以其标准的收敛速率保证收敛到约束优化问题的解,且仅使用低秩奇异值分解(SVD)投影到半正定锥,而非最坏情况下所需的计算上不可行的全秩SVD。我们的方法得到了基于Max-Cut实例数据集的数值实验的支持。

英文摘要:

We consider several classes of highly important semidefinite optimization problems that involve both a convex objective function (smooth or nonsmooth) and additional linear or nonlinear smooth and convex constraints, which are ubiquitous in statistics, machine learning, combinatorial optimization, and other domains. We focus on high-dimensional and plausible settings in which the problem admits a low-rank solution which also satisfies a low-rank complementarity condition. We provide several theoretical results proving that, under these circumstances, the well-known Extragradient method, when initialized in the proximity of an optimal primal-dual solution, converges to a solution of the constrained optimization problem with its standard convergence rates guarantees, using only low-rank singular value decompositions (SVD) to project onto the positive semidefinite cone, as opposed to computationally-prohibitive full-rank SVDs required in worst-case. Our approach is supported by numerical experiments conducted with a dataset of Max-Cut instances.

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。

↑