vix.ing · top · new · best · stats · spec

An Information Theory for Preferences

2003/10/23 by Ali E. Abbas
Computer Science · Decision Sciences · Mathematics · Physics and Astronomy · #Analogy #Applied mathematics #Artificial intelligence #Computer science #Cumulative distribution function #Cumulative prospect theory #Decision-Making and Behavioral Economics #Entropy (arrow of time) #Expected utility hypothesis #Forecasting Techniques and Applications #Function (biology) #Information theory #Mathematical economics #Mathematics #Physics #Principle of maximum entropy #Probability density function #Probability distribution #Probability theory #Statistical Mechanics and Entropy #Statistical physics #Statistics #Utility theory #cs.AI

paper · pdf · doi:10.1063/1.1751362

arxiv created 2003/10/23 · openalex publication_date 2004/01/01 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Recent literature in the Maximum Entropy workshop introduced an analogy between cumulative probability distributions and normalized utility functions. Based on this analogy, a utility density function is defined as the derivative of a normalized utility function. A utility density function has the same mathematical properties as a probability density function, and forms the basis of a mathematical correspondence between utility and probability. This paper presents several results that stem from this correspondence, and provides new interpretations to measures of information theory when applied to utility theory.

Citations