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.
An incremental preference elicitation-based approach to learning potentially non-monotonic preferences in multi-criteria sorting
Dalian University of Technology(大连理工大学);University of Alberta(阿尔伯塔大学);Systems Research Institute, Polish Academy of Sciences(波兰科学院系统研究所);Istinye University(伊斯提涅大学)
AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection
Southern University of Science and Technology(南方科技大学);Peking University(北京大学);MSRA(微软亚洲研究院);Shanghai University of Finance and Economics(上海财经大学);Tsinghua University(清华大学)
Information efficient learning of complexly structured preferences: Elicitation procedures and their application to decision making under uncertainty
LMU Munich(慕尼黑大学)
在本文中,我们提出了有效的方法,复杂结构的偏好,并利用这些问题的决策(严重)的不确定性。基于Jansen,Schollmeyer和Augustin(2018,Int. J. Approx.现在,我们设计启发程序和算法,使决策者能够揭示他们潜在的偏好系统(即两个关系,一个编码序数,另一个编码偏好的基数部分),同时必须回答尽可能少的简单排名问题。这里,遵循两种不同的方法。第一种方法直接利用收集的排名数据获得的顺序部分的偏好,而他们的基数部分构建隐含的测量Meta数据的决策者的考虑时间。与此相反,第二种方法也明确elancies的决策者的偏好系统的主要部分,但是,只有一个近似版本。这种近似是通过额外的收集标签的偏好强度在启发过程中获得。对于这两种方法,我们给出的条件下,他们产生的决策者的真实偏好系统,并探讨如何提高其效率。对于后一个目的,除了无数据的方法,我们还讨论了如何有效地指导启发程序,如果以前的启发轮的数据是可用的。最后,我们展示了如何建议的启发式方法可以利用在(严重)不确定性的决策问题。准确地说,我们表明,在某些条件下,最优决策可以找到没有充分指定的偏好系统。
Harvard University(哈佛大学);University of California Berkeley(加州大学伯克利分校);Massachusetts Institute of Technology(麻省理工学院);Ikigai Labs(Ikigai实验室);University of California San Diego(加州大学圣地亚哥分校)
Communication styles and reader preferences of LLM- and human-authored COVID-19 information explanations: a case study
School of Interactive Computing, Georgia Institute of Technology(交互计算学院,佐治亚理工学院);Amazon(亚马逊);Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign(Siebel计算与数据科学学院,伊利诺伊大学厄巴纳-香槟分校)
EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning
College of Cyber Security, Jinan University(暨南大学网络空间安全学院);School of Management, Jinan University(暨南大学管理学院);School of Computer, Sun Yat-sen University(中山大学计算机学院);School of Computer Science and Engineering, South China University of Technology(华南理工大学计算机科学与工程学院);Guangdong Key Laboratory of Data Security and Privacy Preserving(广东省数据安全与隐私保护重点实验室)