arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.06961cs.LGmath.OC
收藏

基于Wasserstein非平稳性的在线随机优化

Online Stochastic Optimization with Wasserstein Based Non-stationarity

New York University(纽约大学)

Jiashuo Jiang, Xiaocheng Li, Jiawei Zhang

摘要:

我们考虑一个一般的在线随机优化问题,多个预算约束在有限的时间段内的地平线。在每个时间段内,揭示了一个奖励函数和多个成本函数,决策者需要从凸和紧凑的行动集中指定一个行动,以收集奖励并消耗预算。每个成本函数对应于一个预算的消耗。在每个周期中,奖励和成本函数都是从一个未知的分布中得出的,这个分布在时间上是非平稳的。决策者的目标是在预算约束下最大化累积报酬。该公式涵盖了广泛的应用,包括在线线性规划和网络收入管理等。在本文中,我们考虑两种设置:(i)数据驱动的设置,其中真实分布是未知的,但先验估计(可能不准确)是可用的;(ii)无信息的设置,其中真实分布是完全未知的。我们提出了一个统一的Wasserstein距离为基础的措施,以量化的不准确性的先验估计设置(i)和非平稳的系统设置(ii)。我们表明,建议的措施导致一个次线性遗憾在这两种设置的可达性的充分必要条件。对于设置(i),我们提出了一个新的算法,它采取了原始-对偶的角度来看,并集成到一个在线的梯度下降过程中的对偶空间的潜在分布的先验信息。该算法也自然延伸到无信息的设置(ii)。在这两种情况下,我们证明了相应的算法实现了最优顺序的遗憾。在数值实验中,我们演示了如何将所提出的算法自然地与重新求解技术相结合,以进一步提高经验性能。

英文摘要:

We consider a general online stochastic optimization problem with multiple budget constraints over a horizon of finite time periods. In each time period, a reward function and multiple cost functions are revealed, and the decision maker needs to specify an action from a convex and compact action set to collect the reward and consume the budget. Each cost function corresponds to the consumption of one budget. In each period, the reward and cost functions are drawn from an unknown distribution, which is non-stationary across time. The objective of the decision maker is to maximize the cumulative reward subject to the budget constraints. This formulation captures a wide range of applications including online linear programming and network revenue management, among others. In this paper, we consider two settings: (i) a data-driven setting where the true distribution is unknown but a prior estimate (possibly inaccurate) is available; (ii) an uninformative setting where the true distribution is completely unknown. We propose a unified Wasserstein-distance based measure to quantify the inaccuracy of the prior estimate in setting (i) and the non-stationarity of the system in setting (ii). We show that the proposed measure leads to a necessary and sufficient condition for the attainability of a sublinear regret in both settings. For setting (i), we propose a new algorithm, which takes a primal-dual perspective and integrates the prior information of the underlying distributions into an online gradient descent procedure in the dual space. The algorithm also naturally extends to the uninformative setting (ii). Under both settings, we show the corresponding algorithm achieves a regret of optimal order. In numerical experiments, we demonstrate how the proposed algorithms can be naturally integrated with the re-solving technique to further boost the empirical performance.

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。

↑