arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.01344math.OC
收藏

分布鲁棒性能优化

Distributionally Robust Performative Optimization

Zhuangzhuang Jia, Yijie Wang, Roy Dong, Grani A. Hanasusanto

AI总结:

针对性能优化中决策依赖分布的不确定性,提出分布鲁棒框架及重复鲁棒风险最小化算法,在多个应用中显著优于现有基线。

摘要:

在性能随机优化中,决策可以影响随机参数的分布,使得数据生成过程本身依赖于决策。在实践中,决策者很少能够获得真实分布映射,而必须依赖不完善的替代模型,这可能导致在错误指定下产生严重次优的解决方案。数据稀缺或收集成本高昂进一步加剧了现实世界中的这些挑战。为了解决这些问题,我们提出了一个用于性能优化的分布鲁棒框架,该框架明确考虑了决策依赖分布中的模糊性。我们的框架引入了三种建模范式,涵盖了机器学习和不确定性下决策中的广泛应用。后一种设置在性能优化文献中此前未被探索。为了解决由此产生的非凸目标函数的难处理性,我们开发了一种名为重复鲁棒风险最小化的迭代算法,该算法在解决一个决策无关的分布鲁棒优化问题和基于先前决策更新模糊集之间交替进行。这种解耦确保了每次迭代的计算可处理性,同时增强了对模型不确定性的鲁棒性。我们提供了与现成求解器兼容的重构形式,并建立了收敛性和次优性的理论保证。在战略分类、收益管理和投资组合优化中的大量数值实验表明,与最先进的基线相比,我们的方法取得了显著的性能提升,凸显了其实际价值。

英文摘要:

In performative stochastic optimization, decisions can influence the distribution of random parameters, rendering the data-generating process itself decision-dependent. In practice, decision-makers rarely have access to the true distribution map and must instead rely on imperfect surrogate models, which can lead to severely suboptimal solutions under misspecification. Data scarcity or costly collection further exacerbates these challenges in real-world settings. To address these challenges, we propose a distributionally robust framework for performative optimization that explicitly accounts for ambiguity in the decision-dependent distribution. Our framework introduces three modeling paradigms that capture a broad range of applications in machine learning and decision-making under uncertainty. This latter setting has not previously been explored in the performative optimization literature. To tackle the intractability of the resulting nonconvex objectives, we develop an iterative algorithm named repeated robust risk minimization, which alternates between solving a decision-independent distributionally robust optimization problem and updating the ambiguity set based on the previous decision. This decoupling ensures computational tractability at each iteration while enhancing robustness to model uncertainty. We provide reformulations compatible with off-the-shelf solvers and establish theoretical guarantees on convergence and suboptimality. Extensive numerical experiments in strategic classification, revenue management, and portfolio optimization demonstrate significant performance gains over state-of-the-art baselines, highlighting the practical value of our approach.

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。

↑