arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1301.0465math.OC
收藏

仿射不变光滑最小化算法

An Optimal Affine Invariant Smooth Minimization Algorithm

Alexandre d'Aspremont, Cristóbal Guzmán, Martin Jaggi

摘要:

我们在Nesterov(1983)中给出了一个仿射不变的加速一阶算法的实现。它的复杂性界是成比例的仿射不变的正则性常数定义相对于Minkowski规范的可行集。我们将这些结果扩展到更一般的问题,使用$p$ -一致凸prox项优化Hölder光滑函数,并导出一个算法,其复杂性更好地适合可行集的几何形状,并适应最佳Hölder光滑参数和最佳梯度Lipschitz常数。最后,我们详细讨论了当可行集是一个$\ell_p$球时匹配复杂度的下界。在这种情况下,我们的上界的迭代复杂度的算法在Nesterov(1983),因此是最佳的目标精度,光滑度和问题的尺寸。

英文摘要:

We formulate an affine invariant implementation of the accelerated first-order algorithm in Nesterov (1983). Its complexity bound is proportional to an affine invariant regularity constant defined with respect to the Minkowski gauge of the feasible set. We extend these results to more general problems, optimizing Hölder smooth functions using $p$-uniformly convex prox terms, and derive an algorithm whose complexity better fits the geometry of the feasible set and adapts to both the best Hölder smoothness parameter and the best gradient Lipschitz constant. Finally, we detail matching complexity lower bounds when the feasible set is an $\ell_p$ ball. In this setting, our upper bounds on iteration complexity for the algorithm in Nesterov (1983) are thus optimal in terms of target precision, smoothness and problem dimension.

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。

↑