arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.04765math.OC
收藏

Frank-Wolfe方法自适应于误差界条件

Frank-Wolfe Method is Automatically Adaptive to Error Bound Condition

Yi Xu, Tianbao Yang

摘要:

误差界条件最近在最优化中重新引起人们的兴趣。它已被用来获得许多流行的算法,包括次梯度法,近端梯度法和加速近端梯度法更快的收敛。然而,在误差界条件下,Frank-Wolfe(FW)方法是否具有更快的收敛速度还不清楚。在这篇短文中,我们对这个问题给出了肯定的回答。我们表明,FW方法(与线搜索的步长)优化强凸集是自动适应的误差界条件的问题。特别地,FW的迭代复杂度可以由$O(\max(1/ε^{1-θ}, \log(1/ε)))$表征,其中$θ\in[0,1]$是表征误差界条件的常数。我们的结果意味着,如果约束集的特征在于一个强凸函数和目标函数可以实现一个较小的值以外的考虑域,那么FW方法享有快速的$O(1/t^2)$。

英文摘要:

Error bound condition has recently gained revived interest in optimization. It has been leveraged to derive faster convergence for many popular algorithms, including subgradient methods, proximal gradient method and accelerated proximal gradient method. However, it is still unclear whether the Frank-Wolfe (FW) method can enjoy faster convergence under error bound condition. In this short note, we give an affirmative answer to this question. We show that the FW method (with a line search for the step size) for optimization over a strongly convex set is automatically adaptive to the error bound condition of the problem. In particular, the iteration complexity of FW can be characterized by $O(\max(1/ε^{1-θ}, \log(1/ε)))$ where $θ\in[0,1]$ is a constant that characterizes the error bound condition. Our results imply that if the constrained set is characterized by a strongly convex function and the objective function can achieve a smaller value outside the considered domain, then the FW method enjoys a fast rate of $O(1/t^2)$.

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。

↑