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 2304.04032math.OC
收藏

一种黎曼近端牛顿法

A Riemannian Proximal Newton Method

Wutao Si, P. -A. Absil, Wen Huang, Rujun Jiang, Simon Vary

AI总结:

本文将黎曼近端牛顿法推广到嵌入子流形上求解带 L1 正则项的优化问题,基于 Weingarten 和半光滑分析证明其局部二次收敛性,并提出与近端梯度法串联的混合版本以实现全局收敛。

摘要:

近年来,近端梯度法及其变体已被推广到黎曼流形上,用于求解具有可加分离结构的优化问题,即 $f + h$,其中 $f$ 连续可微,$h$ 可能非光滑但为凸函数,且具有计算上合理的近端映射。本文将近端牛顿法推广到嵌入子流形上,用于求解 $h(x) = μ\|x\|_1$ 类型的问题。该推广依赖于 Weingarten 分析和半光滑分析。研究表明,在某些合理假设下,黎曼近端牛顿法具有局部二次收敛速率。此外,通过将黎曼近端梯度法与黎曼近端牛顿法串联,给出了一个混合版本。研究表明,如果切换参数选择得当,则该混合方法全局收敛,并且也具有局部二次收敛速率。在随机数据和合成数据上的数值实验用于验证所提出方法的性能。

英文摘要:

In recent years, the proximal gradient method and its variants have been generalized to Riemannian manifolds for solving optimization problems with an additively separable structure, i.e., $f + h$, where $f$ is continuously differentiable, and $h$ may be nonsmooth but convex with computationally reasonable proximal mapping. In this paper, we generalize the proximal Newton method to embedded submanifolds for solving the type of problem with $h(x) = μ\|x\|_1$. The generalization relies on the Weingarten and semismooth analysis. It is shown that the Riemannian proximal Newton method has a local quadratic convergence rate under certain reasonable assumptions. Moreover, a hybrid version is given by concatenating a Riemannian proximal gradient method and the Riemannian proximal Newton method. It is shown that if the switch parameter is chosen appropriately, then the hybrid method converges globally and also has a local quadratic convergence rate. Numerical experiments on random and synthetic data are used to demonstrate the performance of the proposed methods.

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。

↑