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 1609.04869math.NAcs.NA
收藏

Riemannian流形上梯度、次梯度和近端点方法的迭代复杂度

Iteration-complexity of gradient, subgradient and proximal point methods on Riemannian manifolds

IME/UFG(联邦大学戈亚斯州数学与计算研究所)

G. C. Bento, O. P. Ferreira, J. G. Melo

AI总结:

本文研究了Riemannian流形上的优化问题,分析了非负曲率流形上梯度和次梯度方法的迭代复杂度,通过Riemannian凸分析工具和直接探索流形的切空间,获得不同方法的迭代复杂度界,改进了相关结果,并建立了Hadamard流形上近端点方法的迭代复杂度界。

摘要:

本文研究了Riemannian流形上的优化问题,并分析了非负曲率流形上梯度和次梯度方法的迭代复杂度。通过使用Riemannian凸分析工具并直接探索流形的切空间,我们获得了上述方法的不同迭代复杂度界,补充并改进了相关结果。此外,我们还建立了Hadamard流形上近端点方法的迭代复杂度界。

英文摘要:

This paper considers optimization problems on Riemannian manifolds and analyzes iteration-complexity for gradient and subgradient methods on manifolds with non-negative curvature. By using tools from the Riemannian convex analysis and exploring directly the tangent space of the manifold, we obtain different iteration-complexity bounds for the aforementioned methods, complementing and improving related results. Moreover, we also establish iteration-complexity bound for the proximal point method on Hadamard manifolds.

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。

↑