Download PDFOpen PDF in browser

Basic Independence Results for Maximum Entropy Reasoning Based on Relational Conditionals

15 pagesPublished: October 19, 2017

Abstract

Maximum entropy reasoning (ME-reasoning) based on relational conditionals combines both the capability of ME-distributions to express uncertain knowledge in a way that excellently fits to commonsense, and the great expressivity of an underlying first-order logic. The drawbacks of this approach are its high complexity which is generally paired with a costly domain size dependency, and its non-transparency due to the non-existent a priori independence assumptions as against in Bayesian networks. In this paper we present some independence results for ME-reasoning based on the aggregating semantics for relational conditionals that help to disentangle the composition of ME-distributions, and therefore, lead to a problem reduction and provide structural insights into ME-reasoning.

Keyphrases: aggregating semantics, independence results, principle of maximum entropy, relational probabilistic conditionals

In: Christoph Benzmüller, Christine Lisetti and Martin Theobald (editors). GCAI 2017. 3rd Global Conference on Artificial Intelligence, vol 50, pages 36--50

Download PDFOpen PDF in browser