Maximum-Entropy Priors with Derived Parameters in a Specified Distribution

TL;DR

This paper introduces a maximum-entropy method for transforming probability distributions to ensure certain parameters follow a specified distribution, with a proof of optimality and an application to neutrino hierarchy inference.

Contribution

It presents a novel maximum-entropy transformation technique for parameters in probability distributions, supported by theoretical proof and a practical example.

Findings

The method guarantees maximum entropy under the specified constraints.

The approach is applicable to neutrino hierarchy inference.

Theoretical validation of the maximum-entropy property.

Abstract

We propose a method for transforming probability distributions so that parameters of interest are forced into a specified distribution. We prove that this approach is the maximum entropy choice, and provide a motivating example applicable to neutrino hierarchy inference.