arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.01397math.OCcs.LGcs.SYeess.SYstat.ML
收藏

在线随机凸优化:Wasserstein距离变分

Online Stochastic Convex Optimization: Wasserstein Distance Variation

Department of Electrical and Electronic Engineering, The University of Melbourne(墨尔本大学电气与电子工程学院)

Iman Shames, Farhad Farokhi

摘要:

分布鲁棒优化通常是针对一组固定的分布而不是随时间推移而显著漂移的时变分布进行研究(例如,由于经济的潜在扩张和人口统计的演变,金融和社会学中的情况)。这激发了对概率分布的理解条件,使用Wasserstein距离,可用于对时变环境进行建模。然后,我们可以将这些条件与在线随机最优化结合使用,以调整决策。我们考虑了一个在线的近似梯度法来跟踪光滑凸函数的期望值的最小化,该函数由一个随机变量参数化,其概率分布随着时间的推移以与决策者行为的速率相似的速率连续演化。我们重新审视的概念,估计和跟踪误差的启发系统和控制文献,并提供他们的边界下强凸性,Lipschitz的梯度,和界限上的概率分布漂移。此外,注意到计算预测的一般可行集可能不适合在线实现(由于计算的限制),我们提出了一个精确惩罚法。这样做使我们能够放松梯度的一致有界性,并建立跟踪和估计误差的动态遗憾界。我们进一步引入了一个约束收紧的方法,并与收紧量满足约束的概率。

英文摘要:

Distributionally-robust optimization is often studied for a fixed set of distributions rather than time-varying distributions that can drift significantly over time (which is, for instance, the case in finance and sociology due to underlying expansion of economy and evolution of demographics). This motivates understanding conditions on probability distributions, using the Wasserstein distance, that can be used to model time-varying environments. We can then use these conditions in conjunction with online stochastic optimization to adapt the decisions. We considers an online proximal-gradient method to track the minimizers of expectations of smooth convex functions parameterised by a random variable whose probability distributions continuously evolve over time at a rate similar to that of the rate at which the decision maker acts. We revisit the concepts of estimation and tracking error inspired by systems and control literature and provide bounds for them under strong convexity, Lipschitzness of the gradient, and bounds on the probability distribution drift. Further, noting that computing projections for a general feasible sets might not be amenable to online implementation (due to computational constraints), we propose an exact penalty method. Doing so allows us to relax the uniform boundedness of the gradient and establish dynamic regret bounds for tracking and estimation error. We further introduce a constraint-tightening approach and relate the amount of tightening to the probability of satisfying the constraints.

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。

↑