arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.05765math.OC
收藏

相对Lipschitz连续凸优化问题的自适应算法

Adaptive Algorithms for Relatively Lipschitz Continuous Convex Optimization Problems

Fedor Stonyakin, Alexander Titov, Mohammad Alkousa, Oleg Savchuk, Alexander Gasnikov

AI总结:

针对相对Lipschitz连续凸优化问题,引入人工不精确度提出自适应优化方法及通用自适应方法,具备最优收敛速率,适用范围更广,并给出数值实验结果。

摘要:

近年来,学界提出了一些创新的凸优化概念,即相对光滑性[1]和相对强凸性[2,3]。这些方法极大拓展了梯度类方法的适用范围,且这类方法具备与问题维度无关的最优收敛速率估计。随后,Yu. Nesterov和H. Lu针对带有对应Lipschitz条件类似形式(即所谓相对Lipschitz连续性)的凸最小化问题,对Mirror Descent(镜像下降)方法进行了若干改进。通过向优化模型引入人工不精确度,我们提出了用于最小化凸Lipschitz连续函数以及对应类变分不等式问题的自适应方法。我们还研究了一种自适应“通用”方法,它既适用于相对光滑泛函类的凸最小化问题,也适用于相对Lipschitz连续泛函类的凸最小化问题,且具备最优收敛速率估计。该方法的通用性使得我们能够证明所得理论结果可应用于更广泛的凸优化问题类别。我们同时给出了数值实验的结果。

英文摘要:

Recently there were proposed some innovative convex optimization concepts, namely, relative smoothness [1] and relative strong convexity [2,3]. These approaches have significantly expanded the class of applicability of gradient-type methods with optimal estimates of the convergence rate, which are invariant regardless of the dimensionality of the problem. Later Yu. Nesterov and H. Lu introduced some modifications of the Mirror Descent method for convex minimization problems with the corresponding analogue of the Lipschitz condition (so-called relative Lipschitz continuity). By introducing an artificial inaccuracy to the optimization model, we propose adaptive methods for minimizing a convex Lipschitz continuous function, as well as for the corresponding class of variational inequalities. We also consider an adaptive "universal" method, applicable to convex minimization problems both on the class of relatively smooth and relatively Lipschitz continuous functionals with optimal estimates of the convergence rate. The universality of the method makes it possible to justify the applicability of the obtained theoretical results to a wider class of convex optimization problems. We also present the results of numerical experiments.

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。

↑