Re: [UAI] Calculating joint over arbitrary sets of variables

From: Marco Valtorta (mgv@cs.sc.edu)
Date: Fri Apr 07 2000 - 11:30:12 PDT

  • Next message: Kipersztok, Oscar: "[UAI] Boeing job opportunity"

    Dear Kevin:

    On Fri, 7 Apr 2000, Kevin Murphy wrote:

    > You can use the variable elimination algorithm (pushing sums inside
    > products) to compute a marginal on any *single* set of nodes in one pass
    > over the network. (Choosing an optimal summation ordering is NP-hard.)

    Mark Bloemeke showed how to extend the variable elimination algorithm to
    compute all marginals on single variables as well as the marginal on one
    single set of nodes. For details, see:

    Bloemeke, M. and M. Valtorta. "A Hybrid Algorithm to Compute Marginal and
    Joint Beliefs in Bayesian Networks and Its Complexity." UAI-98, pp.16-23.

    Mark Bloemeke 's Ph.D. dissertation also includes an extension (using
    something called "multiply headed factor trees") to the computation of
    multiple joints. As far as I know, this has not yet been published
    outside the dissertation. This thread tells me that it should be!
    (Mark, are you listening? :-)

    >
    > % For details, see
    > % - R. Dechter, "Bucket Elimination: A Unifying Framework for
    > Probabilistic Inference", UA1 96, pp. 211-219.
    > % - Z. Li and B. D'Ambrosio, "Efficient inference in Bayes networks as a
    > combinatorial
    > % optimization problem", Intl. J. Approximate Reasoning,
    > 11(1):55-81, 1994
    > % - R. McEliece and S. M. Aji, "The Generalized Distributive Law", IEEE
    > Trans. Inform. Theory, to appear
    >
    > HTH,
    > Kevin
    >
    >

    Cheers,

                                    Marco

    Marco Valtorta, Associate Professor (on sabbatical leave in 1999/2000)
    Department of Computer Science mgv@usceast.cs.sc.edu, mgv@cs.auc.dk (March)
    University of South Carolina tel.: (1)(803)777-4641 fax: -3767
    Columbia, SC 29208, U.S.A. http://www.cs.sc.edu/~mgv/ tlx: 805038 USC
    - ---------------------------------------------------------------------------
    "Probability is not about numbers. It is about the structure of reasoning."
                                    --Glenn Shafer
    - ---------------------------------------------------------------------------

    ------- End of Forwarded Message



    This archive was generated by hypermail 2b29 : Fri Apr 07 2000 - 11:32:05 PDT