arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1307.5449math.PRcs.LGstat.ML
收藏

非平稳随机最优化

Non-stationary Stochastic Optimization

Columbia University(哥伦比亚大学);Stanford University(斯坦福大学)

O. Besbes, Y. Gur, A. Zeevi

摘要:

我们考虑序列随机最优化问题的一个非平稳变体,其中底层的费用函数可能会沿水平方向变化。我们提出了一个措施,称为变化预算,控制的程度说,变化,并研究如何限制这个预算的影响可实现的性能。我们确定尖锐的条件下,它是可能实现长期平均最优性和更精细的性能指标,如率最优性,充分表征这些问题的复杂性。在这样做的过程中,我们还建立了两个相当不同的文学链之间的强有力的连接:对抗在线凸优化;和更传统的随机逼近范式(在非平稳设置)。这种联系是通过利用前者的最佳政策结构来在后者中获得良好表现的政策的关键。最后,极小极大遗憾的严格界限使我们能够量化“非平稳性的代价”,这在数学上捕捉到了嵌入在一个随时间变化的环境与一个静止的环境中增加的复杂性。

英文摘要:

We consider a non-stationary variant of a sequential stochastic optimization problem, in which the underlying cost functions may change along the horizon. We propose a measure, termed variation budget, that controls the extent of said change, and study how restrictions on this budget impact achievable performance. We identify sharp conditions under which it is possible to achieve long-run-average optimality and more refined performance measures such as rate optimality that fully characterize the complexity of such problems. In doing so, we also establish a strong connection between two rather disparate strands of literature: adversarial online convex optimization; and the more traditional stochastic approximation paradigm (couched in a non-stationary setting). This connection is the key to deriving well performing policies in the latter, by leveraging structure of optimal policies in the former. Finally, tight bounds on the minimax regret allow us to quantify the "price of non-stationarity," which mathematically captures the added complexity embedded in a temporally changing environment versus a stationary one.

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。

↑