Fully Bayesian Unfolding

TL;DR

This paper introduces a fully Bayesian unfolding method that applies Bayesian inference to derive a posterior probability distribution for the true spectrum, offering a probabilistic approach to the unfolding problem.

Contribution

The paper presents a novel fully Bayesian unfolding (FBU) method that directly computes a posterior distribution for the true spectrum, differing from previous iterative techniques.

Findings

Provides a posterior probability density for the unfolded spectrum.

Uses a non-constant prior for regularization.

Distinguishes itself from D'Agostini's iterative method.

Abstract

Bayesian inference is applied directly to the problem of unfolding. The outcome is a posterior probability density for the spectrum before smearing, defined in the multi-dimensional space of all possible spectra. Regularization consists in choosing a non-constant prior. Despite some similarity, the fully bayesian unfolding (FBU) method, presented here, should not be confused with D'Agostini's iterative method.