MESA: Maximum Entropy by Simulated Annealing

TL;DR

The paper introduces MESA, an algorithm that uses simulated annealing to compute maximum entropy joint distributions in probabilistic reasoning systems, effectively handling conflicting rules and large networks.

Contribution

MESA is a novel method that applies simulated annealing to derive maximum entropy distributions, accommodating reliability and conflicts in probabilistic inference.

Findings

Handles large inference networks efficiently

Resolves conflicts between contradictory probabilistic statements

Provides high-precision probability estimates

Abstract

Probabilistic reasoning systems combine different probabilistic rules and probabilistic facts to arrive at the desired probability values of consequences. In this paper we describe the MESA-algorithm (Maximum Entropy by Simulated Annealing) that derives a joint distribution of variables or propositions. It takes into account the reliability of probability values and can resolve conflicts between contradictory statements. The joint distribution is represented in terms of marginal distributions and therefore allows to process large inference networks and to determine desired probability values with high precision. The procedure derives a maximum entropy distribution subject to the given constraints. It can be applied to inference networks of arbitrary topology and may be extended into a number of directions.