In this paper, we study a class of bilevel optimization problems, also known as simple bilevel optimization, where we minimize a smooth objective function over the optimal solution set of another convex constrained optimization problem. Several iterative methods have been developed for tackling this class of problems. Alas, their convergence guarantees are either asymptotic for the upper-level objective, or the convergence rates are slow and sub-optimal. To address this issue, in this paper, we introduce a novel bilevel optimization method that locally approximates the solution set of the lower-level problem via a cutting plane, and then runs a conditional gradient update to decrease the upper-level objective. When the upper-level objective is convex, we show that our method requires ${\mathcal{O}}(\max\{1/\epsilon_f,1/\epsilon_g\})$ iterations to find a solution that is $\epsilon_f$-optimal for the upper-level objective and $\epsilon_g$-optimal for the lower-level objective. Moreover, when the upper-level objective is non-convex, our method requires ${\mathcal{O}}(\max\{1/\epsilon_f^2,1/(\epsilon_f\epsilon_g)\})$ iterations to find an $(\epsilon_f,\epsilon_g)$-optimal solution. We also prove stronger convergence guarantees under the H\"olderian error bound assumption on the lower-level problem. To the best of our knowledge, our method achieves the best-known iteration complexity for the considered class of bilevel problems.
翻译:在本文中, 我们研究一组双级优化问题, 也称为简单双级优化, 在那里我们将一个平滑的目标功能最小化到另一个 convex 限制优化问题的最佳解决方案组。 已经开发了几种迭代方法来解决这组问题。 唉, 它们的趋同保障对于上层目标来说要么是零, 或者趋同率是缓慢和亚最佳的。 为了解决这个问题, 在本文中, 我们引入了一种新的双级优化方法, 通过切开平面来接近较低层问题的解决方案集, 然后运行一个有条件的梯度更新以降低上层目标 。 当上层趋同目标为 convex 时, 我们的方法需要 $\ max cal_ liver_ levelment2; (\\ liver_ liver_ lixion_ lixion_ lix legal_ legal_ liver) 找到上层目标的答案, 也就是我们最高级目标( liver_ liver_ liver_ ton_ ltom_ ltus legal legal legal) sution sution sution sublegal sublement sublement sublement sublemental_ real_ real_ real_ real_ intal_ yal_ intal_ intal_ intal_ intmental_ intmental_ legal_ legal_ real_ legal_ legal_ legal_ g) intment ( 我们 intmental_ real_ int)