arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.00558math.OCcs.LGstat.ML
收藏

再论多胞形的Frank-Wolfe:严格互补性与稀疏性

Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity

Technion - Israel Institute of Technology(以色列理工学院)

Dan Garber

摘要:

近年来,在假设目标函数具有二次增长性质的条件下,证明了求解凸紧多面体上光滑凸极小化问题的经典Frank-Wolfe算法(又称条件梯度算法)的简单修改以线性速度收敛。然而,这些方法的速度明显取决于问题的维度,这不能解释它们在大规模问题中的经验成功。在本文中,我们首先证明,已经非常简单的问题,甚至当最优解位于低维面的多面体,这种依赖的尺寸不能避免在最坏的情况下。然后,我们重新审视了一个严格的互补性假设已经考虑在沃尔夫的经典书籍\cite{Wolfe1970},并证明在这种条件下,弗兰克-沃尔夫方法与远离步骤和线搜索的线性收敛率,明确地只依赖于最佳面的尺寸。我们激励严格互补证明,它意味着稀疏鲁棒性的最优解噪声。

英文摘要:

In recent years it was proved that simple modifications of the classical Frank-Wolfe algorithm (aka conditional gradient algorithm) for smooth convex minimization over convex and compact polytopes, converge with linear rate, assuming the objective function has the quadratic growth property. However, the rate of these methods depends explicitly on the dimension of the problem which cannot explain their empirical success for large scale problems. In this paper we first demonstrate that already for very simple problems and even when the optimal solution lies on a low-dimensional face of the polytope, such dependence on the dimension cannot be avoided in worst case. We then revisit the addition of a strict complementarity assumption already considered in Wolfe's classical book \cite{Wolfe1970}, and prove that under this condition, the Frank-Wolfe method with away-steps and line-search converges linearly with rate that depends explicitly only on the dimension of the optimal face. We motivate strict complementarity by proving that it implies sparsity-robustness of optimal solutions to noise.

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。

↑