Tractability through Exchangeability: A New Perspective on Efficient Probabilistic Inference
Abstract
Exchangeability is a central notion in statistics and probability theory. The assumption that an infinite sequence of data points is exchangeable is at the core of Bayesian statistics. However, finite exchangeability as a statistical property that renders probabilistic inference tractable is less wellunderstood. We develop a theory of finite exchangeability and its relation to tractable probabilistic inference. The theory is complementary to that of independence and conditional independence. We show that tractable inference in probabilistic models with high treewidth and millions of variables can be understood using the notion of finite (partial) exchangeability. We also show that existing lifted inference algorithms implicitly utilize a combination of conditional independence and partial exchangeability.
 Publication:

arXiv eprints
 Pub Date:
 January 2014
 arXiv:
 arXiv:1401.1247
 Bibcode:
 2014arXiv1401.1247N
 Keywords:

 Computer Science  Artificial Intelligence
 EPrint:
 In Proceedings of the 28th AAAI Conference on Artificial Intelligence