Proximal Regularization for the Saddle Point Gradient Dynamics

Proximal Regularization for the Saddle Point Gradient Dynamics
复制标题

鞍点梯度动力学的近端正则化

DOI:
--
复制
发表时间:
2021
影响因子:
6.8
通讯作者:
F. Paganini
F. Paganini
中科院分区:
计算机科学2区
文献类型:
--
作者:
Diego Goldsztajn;F. Paganini

文献摘要

被引文献

相似文献

利用鞍点梯度动力学方法研究了一类凸优化问题的求解.而不是使用标准的拉格朗日函数是经典的,在这种方法中,我们认为通过一个近似的最小化步骤得到的正则化拉格朗日。我们表明,没有假设的光滑性或严格的凸性在原问题中,正则化拉格朗日是光滑的,并导致全局收敛的鞍点动力学。该方法通过云计算资源分配的应用程序进行了演示。
This article concerns the solution of a convex optimization problem through the saddle point gradient dynamics. Instead of using the standard Lagrangian as is classical in this method, we consider a regularized Lagrangian obtained through a proximal minimization step. We show that, without assumptions of smoothness or strict convexity in the original problem, the regularized Lagrangian is smooth and leads to globally convergent saddle point dynamics. The method is demonstrated through an application to resource allocation in cloud computing.