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 2112.09291math.OC
收藏

基于新子问题重构的二阶复杂度保证的三次正则化方法

Cubic regularization methods with second-order complexity guarantee based on a new subproblem reformulation

Rujun Jiang, Zhishuo Zhou, Zirui Zhou

摘要:

立方正则化(CR)算法近年来在文献中引起了很多关注。我们提出了一个新的三次正则化子问题。重新制定是一个无约束的凸问题,需要计算的最小特征值的海森。然后,基于这种重新制定,我们推导出一个变种的(非自适应)CR提供了一个已知的Lipschitz常数的Hessian和一个变种的自适应正则化与立方(ARC)。我们表明,我们的变体的迭代复杂度与使用一阶和二阶信息的无约束极小化算法的最佳已知界限相匹配。此外,我们表明,我们的两个变种的操作复杂性也符合国家的最先进的界限在文献中。对CUTEst集上的测试问题进行的数值实验表明,基于我们新的子问题重构的ARC与现有的算法具有可比性。

英文摘要:

The cubic regularization (CR) algorithm has attracted a lot of attentions in the literature in recent years. We propose a new reformulation of the cubic regularization subproblem. The reformulation is an unconstrained convex problem that requires computing the minimum eigenvalue of the Hessian. Then based on this reformulation, we derive a variant of the (non-adaptive) CR provided a known Lipschitz constant for the Hessian and a variant of adaptive regularization with cubics (ARC). We show that the iteration complexity of our variants matches the best known bounds for unconstrained minimization algorithms using first- and second-order information. Moreover, we show that the operation complexity of both of our variants also matches the state-of-the-art bounds in the literature. Numerical experiments on test problems from CUTEst collection show that the ARC based on our new subproblem reformulation is comparable to existing algorithms.

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。

↑