arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1105.2176math.OCcs.ITcs.LGcs.SYeess.SYmath.IT
收藏

有限信息下的优化框架

A Framework for Optimization under Limited Information

Technical University Berlin(柏林工业大学);Deutsche Telekom Laboratories(德国电信实验室)

Tansu Alpcan

AI总结:

针对有限信息下的优化问题,提出一个融合信息收集、估计和优化的统一框架,采用贝叶斯方法和高斯过程回归,并利用信息论熵量化信息获取。

摘要:

在许多现实世界问题中,优化决策必须在信息有限的情况下做出。决策者可能没有关于通常非凸目标函数的先验或后验数据,只能通过随时间推移的昂贵观测获得有限数量的点。本文提出了一个优化框架,以整体和结构化的方式考虑信息收集(观测)、估计(回归)和优化(最大化)方面。通过使用信息论中的熵度量显式量化每个优化步骤中获取的信息,采用贝叶斯方法并使用高斯过程作为最先进的回归方法,对要优化(最大化)的(非凸)目标函数进行建模和估计。由此产生的迭代方案允许决策者通过同时定量表达每个方面的偏好来解决问题。

英文摘要:

In many real world problems, optimization decisions have to be made with limited information. The decision maker may have no a priori or posteriori data about the often nonconvex objective function except from on a limited number of points that are obtained over time through costly observations. This paper presents an optimization framework that takes into account the information collection (observation), estimation (regression), and optimization (maximization) aspects in a holistic and structured manner. Explicitly quantifying the information acquired at each optimization step using the entropy measure from information theory, the (nonconvex) objective function to be optimized (maximized) is modeled and estimated by adopting a Bayesian approach and using Gaussian processes as a state-of-the-art regression method. The resulting iterative scheme allows the decision maker to solve the problem by expressing preferences for each aspect quantitatively and concurrently.

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。

↑