Log In Sign Up

Credal Networks under Maximum Entropy

by   Thomas Lukasiewicz, et al.

We apply the principle of maximum entropy to select a unique joint probability distribution from the set of all joint probability distributions specified by a credal network. In detail, we start by showing that the unique joint distribution of a Bayesian tree coincides with the maximum entropy model of its conditional distributions. This result, however, does not hold anymore for general Bayesian networks. We thus present a new kind of maximum entropy models, which are computed sequentially. We then show that for all general Bayesian networks, the sequential maximum entropy model coincides with the unique joint distribution. Moreover, we apply the new principle of sequential maximum entropy to interval Bayesian networks and more generally to credal networks. We especially show that this application is equivalent to a number of small local entropy maximizations.


page 1

page 2

page 4

page 5

page 6

page 8


Dirichlet Bayesian Network Scores and the Maximum Entropy Principle

A classic approach for learning Bayesian networks from data is to select...

Maximum entropy priors with derived parameters in a specified distribution

We propose a method for transforming probability distributions so that p...

MESA: Maximum Entropy by Simulated Annealing

Probabilistic reasoning systems combine different probabilistic rules an...

Maximum Entropy Principle Analysis in Network Systems with Short-time Recordings

In many realistic systems, maximum entropy principle (MEP) analysis prov...

A Distribution Similarity Based Regularizer for Learning Bayesian Networks

Probabilistic graphical models compactly represent joint distributions b...

Low probability states, data statistics, and entropy estimation

A fundamental problem in analysis of complex systems is getting a reliab...

Entropy and Belief Networks

The product expansion of conditional probabilities for belief nets is no...