Conditioning Algorithms for Exact and Approximate Inference in Causal Networks

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.

Cite

Text

Darwiche. "Conditioning Algorithms for Exact and Approximate Inference in Causal Networks." Conference on Uncertainty in Artificial Intelligence, 1995.

Markdown

[Darwiche. "Conditioning Algorithms for Exact and Approximate Inference in Causal Networks." Conference on Uncertainty in Artificial Intelligence, 1995.](https://mlanthology.org/uai/1995/darwiche1995uai-conditioning/)

BibTeX

@inproceedings{darwiche1995uai-conditioning,
  title     = {{Conditioning Algorithms for Exact and Approximate Inference in Causal Networks}},
  author    = {Darwiche, Adnan},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {1995},
  pages     = {99-107},
  url       = {https://mlanthology.org/uai/1995/darwiche1995uai-conditioning/}
}