arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.06457math.OC
收藏

多目标Frank-Wolfe方法的改进收敛速率

Improved convergence rates for the multiobjective Frank-Wolfe method

Douglas S. Gonçalves, Max L. N. Gonçalves, Jefferson G. Melo

AI总结:

本文针对凸约束多目标优化中的Frank-Wolfe方法,在不同目标函数、可行集和极限点条件下建立了改进收敛速率,并给出实例验证。

摘要:

本文分析了用于求解凸约束多目标优化的Frank-Wolfe方法的收敛速率。我们在关于目标函数、可行集以及该方法所生成序列的极限点位置的不同假设下,建立了改进的收敛速率。就目标函数值而言,我们首先证明:如果目标函数是强凸的,并且该方法所生成序列的极限点位于可行集的相对内部,那么该算法达到线性收敛速率。接下来,我们关注一类特殊问题,其中可行约束集对某个$α>0$和$q \geq 2$是$(α,q)$-一致凸的,特别包括所有$p>1$的$\ell_p$-球。在这一背景下,我们证明该方法获得:(i) 当目标函数强凸时,速率为$\mathcal{O}(1/k^\frac{q}{q-1})$;(ii) 在一个额外假设下,如果$q=2$则为线性速率,如果$q>2$则为$\mathcal{O}(1/k^{\frac{q}{q-2}})$的速率,而该额外假设在可行集不包含无约束弱Pareto点时总是成立。我们还讨论了该算法在最优性度量方面的增强收敛速率。最后,我们提供一些简单例子来说明这些收敛速率和假设集合。

英文摘要:

This paper analyzes the convergence rates of the {\it Frank-Wolfe } method for solving convex constrained multiobjective optimization. We establish improved convergence rates under different assumptions on the objective function, the feasible set, and the localization of the limit point of the sequence generated by the method. In terms of the objective function values, we firstly show that if the objective function is strongly convex and the limit point of the sequence generated by the method lies in the relative interior of the feasible set, then the algorithm achieves a linear convergence rate. Next, we focus on a special class of problems where the feasible constraint set is $(α,q)$-uniformly convex for some $α>0$ and $q \geq 2$, including, in particular, \(\ell_p\)-balls for all $p>1$. In this context, we prove that the method attains: (i) a rate of $\mathcal{O}(1/k^\frac{q}{q-1})$ when the objective function is strongly convex; and (ii) a linear rate (if $q=2$) or a rate of $\mathcal{O}(1/k^{\frac{q}{q-2}})$ (if $q>2$) under an additional assumption, which always holds if the feasible set does not contain an unconstrained weak Pareto point. We also discuss enhanced convergence rates for the algorithm in terms of an optimality measure. Finally, we provide some simple examples to illustrate the convergence rates and the set of assumptions.

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。

↑