Optimization Methods & Software ( IF 1.4 ) Pub Date : 2020-04-23 , DOI: 10.1080/10556788.2020.1731749 G.N. Grapiglia 1 , Yu. Nesterov 2
ABSTRACT
In this paper, we study the auxiliary problems that appear in p-order tensor methods for unconstrained minimization of convex functions with ν-Hölder continuous pth derivatives. This type of auxiliary problems corresponds to the minimization of a -order regularization of the pth-order Taylor approximation of the objective. For the case p = 3, we consider the use of Gradient Methods with Bregman distance. When the regularization parameter is sufficiently large, we prove that the referred methods take at most iterations to find either a suitable approximate stationary point of the tensor model or an ε-approximate stationary point of the original objective function.
中文翻译:
张量法凸优化问题辅助问题的不精确解
摘要
在本文中,我们研究了用ν- Hölder连续p次导数无约束最小化p阶张量方法中出现的辅助问题。这种类型的辅助问题对应于最小化目标的p阶泰勒近似的2阶正则化。对于p = 3的情况,我们考虑使用Bregman距离的梯度方法。当正则化参数足够大时,我们证明所引用的方法最多迭代以找到张量模型的合适的近似平稳点或原始目标函数的ε近似平稳点。