arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv cs/0310045cs.AI
收藏

偏好的信息论

An information theory for preferences

Ali E. Abbas

摘要:

最近的文献在最大熵研讨会上介绍了累积概率分布和归一化效用函数之间的类比。基于这个类比,效用密度函数可以定义为归一化效用函数的导数。效用密度函数是非负的,并且积分为1。这两个性质构成了效用和概率之间对应关系的基础。这种类比的一个自然应用是最大熵原理来分配最大熵效用值。最大熵效用根据分配所需的偏好信息解释许多常见的效用函数,并根据部分偏好信息帮助分配效用值。本文回顾了最大熵效用,并介绍了进一步的结果,源于概率和效用之间的对偶。

英文摘要:

Recent literature in the last Maximum Entropy workshop introduced an analogy between cumulative probability distributions and normalized utility functions. Based on this analogy, a utility density function can de defined as the derivative of a normalized utility function. A utility density function is non-negative and integrates to unity. These two properties form the basis of a correspondence between utility and probability. A natural application of this analogy is a maximum entropy principle to assign maximum entropy utility values. Maximum entropy utility interprets many of the common utility functions based on the preference information needed for their assignment, and helps assign utility values based on partial preference information. This paper reviews maximum entropy utility and introduces further results that stem from the duality between probability and utility.

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。

↑