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 2312.02612math.OC
收藏

凸优化的方向近端点法

Directional proximal point method for convex optimization

Wen-Liang Hwang, Chang-Wei Yueh

AI总结:

本文提出方向近端点法(Direction PPM),通过沿特定方向进行近端正则化降低高维凸优化中近端点算子的计算成本,并给出方向序列的收敛条件及实验验证。

摘要:

当函数的维数(即变量个数)较高时,使用近端点算子进行优化可能在计算上代价高昂。在本研究中,我们试图通过构造一种方向算子来降低计算近端点算子的成本,该算子对函数沿特定方向的近端正则化进行惩罚。我们将该算子用于一种新的优化方法,称为方向近端点法(Direction PPM)。使用 Direction PPM 时,实现收敛的关键在于为方向近端点算子选择方向序列。本文给出了可为凸函数推导出能够实现全局收敛的方向所需的条件/假设。Direction PPM 可视为 PPM 的轻量版本,它利用标量优化通过方向包络函数推导出稳定步长,并利用辅助方法推导出满足这些假设的方向序列。这使得 Direction PPM 能够适用于更大类的函数。通过对可微凸函数的应用,我们证明当前迭代点处的负梯度方向可能被用于实现这一目标。我们提供了实验结果,以说明 Direction PPM 在实际中的有效性。

英文摘要:

The use of proximal point operators for optimization can be computationally expensive when the dimensionality of a function (i.e., the number of variables) is high. In this study, we sought to reduce the cost of calculating proximal point operators by developing a directional operator in which the proximal regularization of a function along a specific direction is penalized. We used this operator in a novel approach to optimization, referred to as the directional proximal point method (Direction PPM). When using Direction PPM, the key to achieving convergence is the selection of direction sequences for directional proximal point operators. In this paper, we present the conditions/assumptions by which to derive directions capable of achieving global convergence for convex functions. Considered a light version of PPM, Direction PPM uses scalar optimization to derive a stable step-size via a direction envelope function and an auxiliary method to derive a direction sequence that satisfies the assumptions. This makes Direction PPM adaptable to a larger class of functions. Through applications to differentiable convex functions, we demonstrate that negative gradient directions at the current iterates could conceivably be used to achieve this end. We provide experimental results to illustrate the efficacy of Direction PPM in practice.

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。

↑