Bayesian networks : a better than frequentist approach for parametrization, and a more accurate structural complexity measure than the number of parameters

Sylvain Gelly, Olivier TeytaudSPIRE 2005

Abstract

We propose and justify a better-than-frequentist approach for bayesian network parametrization, and propose a structural entropy term that more precisely quantifies the complexity of a BN than the number of parameters. Algorithms for BN learning are deduced.
BibTeX
@inproceedings{gelly2005bayesian,
  author = {Sylvain Gelly and Olivier Teytaud},
  title = {{Bayesian networks : a better than frequentist approach for parametrization, and a more accurate structural complexity measure than the number of parameters}},
  booktitle = {SPIRE},
  year = {2005},
}

Loading related content...

Figure