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 2606.03383math.OC
收藏

一种递归的域与目标自适应Frank-Wolfe算法

A Recursive Domain- and Objective-Adaptive Frank-Wolfe Algorithm

University of Konstanz(康斯坦茨大学);University of St.Gallen(圣加仑大学)

Marcel Kaiser, Tobias Sutter

AI总结:

针对域和目标函数均未知的数据驱动优化问题,提出一种递归Frank-Wolfe变体,通过集成估计器保持无投影特性,并证明优化误差随估计精度缩放。

摘要:

我们研究经典Frank-Wolfe算法的一种递归变体,用于在凸紧致域上最小化凸可微函数。与传统设置不同,我们假设问题域和目标函数最初均未知,必须从数据中学习。为此,我们将估计器集成到优化过程中,使算法能够迭代地改进问题域和目标函数的近似。我们的方法保持了经典Frank-Wolfe算法的无投影特性,同时适应数据驱动设置中固有的不确定性。我们建立了递归方法的收敛保证,表明优化误差随学习估计器的精度缩放。两个实验支持我们的理论发现,表明所提方法在问题域和目标函数精确已知的情况下,实现了与经典Frank-Wolfe算法相当的收敛行为,同时提供了显著的计算节省。

英文摘要:

We investigate a recursive variant of the classical Frank-Wolfe algorithm for minimizing a convex differentiable function over a convex compact domain. Unlike the traditional setting, we assume that both the problem domain and the objective function are initially unknown and must be learned from data. To address this, we integrate estimators into the optimization process, allowing the algorithm to iteratively refine approximations of the problem domain and the objective function. Our approach maintains the projection-free nature of the classical Frank-Wolfe algorithm while adapting to the uncertainty inherent in data-driven settings. We establish convergence guarantees for the recursive method, showing that the optimization error scales with the accuracy of the learned estimators. Two experiments support our theoretical findings, demonstrating that the proposed method achieves convergence behavior comparable to that of the classical Frank-Wolfe algorithm under exact knowledge of the problem domain and objective function, while offering significant computational savings.

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。

↑