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 2508.08856math.OC
收藏

约束决策依赖优化的投影梯度下降

Projected Gradient Descent for Constrained Decision-Dependent Optimization

Zifan Wang, Changxin Liu, Thomas Parisini, Michael M. Zavlanos, Karl H. Johansson

AI总结:

本文针对决策依赖优化问题,提出重复投影梯度下降(RPGD)方法,通过向不断演变的可行集迭代投影确保连续可行性,并证明其收敛性且计算负担更低。

摘要:

本文考虑决策依赖优化问题,其中数据分布对决策作出反应,从而同时影响目标函数和线性约束。我们提出了一种称为重复投影梯度下降(RPGD)的新方法,该方法在优化过程中迭代地将点投影到不断演变的可行集上。为了分析不同投影集的影响,我们证明了向不同集合投影的Lipschitz连续性,并给出了显式的Lipschitz常数。利用这一性质,我们为RPGD收敛到约束均衡点提供了充分条件。与现有的双重上升方法相比,RPGD确保了优化过程中的连续可行性,并减轻了计算负担。我们通过市场问题和动态定价问题的数值实验验证了结果。

英文摘要:

This paper considers the decision-dependent optimization problem, where the data distributions react in response to decisions affecting both the objective function and linear constraints. We propose a new method termed repeated projected gradient descent (RPGD), which iteratively projects points onto evolving feasible sets throughout the optimization process. To analyze the impact of varying projection sets, we show a Lipschitz continuity property of projections onto varying sets with an explicitly given Lipschitz constant. Leveraging this property, we provide sufficient conditions for the convergence of RPGD to the constrained equilibrium point. Compared to the existing dual ascent method, RPGD ensures continuous feasibility throughout the optimization process and reduces the computational burden. We validate our results through numerical experiments on a market problem and dynamic pricing problem.

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。

↑