English

Conditioning Methods for Exact and Approximate Inference in Causal Networks

Artificial Intelligence 2013-02-21 v1

Abstract

We present two algorithms for exact and approximate inference in causal networks. The first algorithm, dynamic conditioning, is a refinement of cutset conditioning that has linear complexity on some networks for which cutset conditioning is exponential. The second algorithm, B-conditioning, is an algorithm for approximate inference that allows one to trade-off the quality of approximations with the computation time. We also present some experimental results illustrating the properties of the proposed algorithms.

Keywords

Cite

@article{arxiv.1302.4939,
  title  = {Conditioning Methods for Exact and Approximate Inference in Causal Networks},
  author = {Adnan Darwiche},
  journal= {arXiv preprint arXiv:1302.4939},
  year   = {2013}
}

Comments

Appears in Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence (UAI1995)

R2 v1 2026-06-21T23:29:23.579Z