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 2406.09786math.OC
收藏

面向凸优化问题的带广义正则项的正则化牛顿法收敛性分析

Convergence analysis of a regularized Newton method with generalized regularization terms for convex optimization problems

Yuya Yamakawa, Nobuo Yamashita

AI总结:

针对无约束凸优化问题,提出带广义正则项的通用正则化牛顿法框架,涵盖多种现有及新型RNM,证明其具有与三次RNM一致的全局$\u2a7c(k^{-2})$和局部超线性收敛性。

摘要:

本文针对无约束凸优化问题,提出一种带广义正则项的正则化牛顿法(RNM)。该广义正则项将二次、三次及弹性网(elastic net)正则项作为特例包含在内,因此所提方法是一个通用框架,既涵盖经典与三次RNM,也包含一种新型的带弹性网正则的RNM。本文证明,所提RNM具有全局$\u2a7c(k^{-2})$收敛性和局部超线性收敛性,与三次RNM的收敛性质一致。

英文摘要:

This paper presents a regularized Newton method (RNM) with generalized regularization terms for unconstrained convex optimization problems. The generalized regularization includes quadratic, cubic, and elastic net regularizations as special cases. Therefore, the proposed method serves as a general framework that includes not only the classical and cubic RNMs but also a novel RNM with elastic net regularization. We show that the proposed RNM has the global $\mathcal{O}(k^{-2})$ and local superlinear convergence, which are the same as those of the cubic RNM.

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。

↑