PAC-learning bounded tree-width Graphical Models

  title={PAC-learning bounded tree-width Graphical Models},
  author={Mukund Narasimhan and Jeff A. Bilmes},
We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Previous approaches to this problem, such as those of Chow ([1]), and Hoffgen ([7]) have shown that this class is PAClearnable by reducing it to a combinatorial optimization problem. However, for k > 1, this problem is NPcomplete ([15]), and so unless P=NP, these approaches will take exponential amounts of time. Our… CONTINUE READING
Highly Cited
This paper has 72 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 2 times over the past 90 days. VIEW TWEETS
51 Citations
17 References
Similar Papers


Publications citing this paper.

72 Citations

Citations per Year
Semantic Scholar estimates that this publication has 72 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 17 references

Efficient proper PAC-learning of bounded treewidth graphical models

  • M. Narasimhan, J. Bilmes
  • Technical Report UWEETR-2004-0009, University of…
  • 2004

Graph Classes : A Survey

  • A. Brandstädt, V. B. Lee, J. P. Spinrad
  • SIAM Monographs on Discrete Mathematics and…
  • 1999

Topics in Intersection Graph Theory

  • T. A. McKee, F. R. McMorris
  • SIAM Monographs on Discrete Mathematics and…
  • 1999

Graphical Models

  • S. Lauritzen
  • Oxford University Press, Oxford, United Kingdom
  • 1996

Similar Papers

Loading similar papers…