arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.05415math.OC
收藏

基于二分法的近最优凸简单双层优化

Near-Optimal Convex Simple Bilevel Optimization with a Bisection Method

Jiulin Wang, Xu Shi, Rujun Jiang

AI总结:

针对复合凸简单双层优化,本文提出通过检验不等式系统可行性进行区间收缩的二分算法,在上下层分别达到 $ε_f$、$ε_g$ 最优时获得近最优复杂度,并由数值实验验证有效性。

摘要:

本文研究一类简单双层优化问题,其中在上层最小化一个复合凸函数,并受限于一个复合凸下层问题。现有方法要么只能为上层目标提供渐近保证,要么只能达到较慢的次线性收敛速率。我们提出一种二分算法,用于寻找对上层目标为 $ε_f$-最优且对下层目标为 $ε_g$-最优的解。在每次迭代中,二分搜索通过评估不等式系统的可行性来缩小区间。在温和条件下,我们方法的总操作复杂度为 ${\tilde {\mathcal{O}}}\left(\max\{\sqrt{L_{f_1}/ε_f},\sqrt{L_{g_1}/ε_g}\}\right)$。这里,一次单位操作可以是函数求值、梯度求值或近端映射调用;$L_{f_1}$ 和 $L_{g_1}$ 分别是上层和下层目标中光滑分量的 Lipschitz 常数,而 ${\tilde {\mathcal{O}}}$ 隐藏对数项。我们的方法实现了近最优速率,在忽略对数项时与无约束光滑或复合凸优化中的最优速率相匹配。数值实验证明了该方法的有效性。

英文摘要:

This paper studies a class of simple bilevel optimization problems where we minimize a composite convex function at the upper-level subject to a composite convex lower-level problem. Existing methods either provide asymptotic guarantees for the upper-level objective or attain slow sublinear convergence rates. We propose a bisection algorithm to find a solution that is $ε_f$-optimal for the upper-level objective and $ε_g$-optimal for the lower-level objective. In each iteration, the binary search narrows the interval by assessing inequality system feasibility. Under mild conditions, the total operation complexity of our method is ${\tilde {\mathcal{O}}}\left(\max\{\sqrt{L_{f_1}/ε_f},\sqrt{L_{g_1}/ε_g} \} \right)$. Here, a unit operation can be a function evaluation, gradient evaluation, or the invocation of the proximal mapping, $L_{f_1}$ and $L_{g_1}$ are the Lipschitz constants of the upper- and lower-level objectives' smooth components, and ${\tilde {\mathcal{O}}}$ hides logarithmic terms. Our approach achieves a near-optimal rate, matching the optimal rate in unconstrained smooth or composite convex optimization when disregarding logarithmic terms. Numerical experiments demonstrate the effectiveness of our method.

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。

↑