[UAI] Survey articles on Learning (Summary, long)

From: Russell Almond (ralmond@ets.org)
Date: Tue Mar 19 2002 - 15:30:51 PST

  • Next message: Gaby Kern-Isberner: "[UAI] CF Participation Workshop "Conditionals, Information, and Inference""

    > Russell Almond wrote:
    >
    >> I'm looking for a good survey article on Learning in Bayesian Networks.
    >> Does anybody know of something like that?
    >>
    >> I will summarize replies to the list.
    >>

    Here is my promised summary.

    The articles I was remembering but not remembering the reference for were:

    > @techreport{ david95tutorial,
    > author = "Heckerman, David",
    > title = "{A} {T}utorial on {L}earning {B}ayesian {N}etworks",
    > number = "MSR-TR-95-06",
    > month = "March",
    > year = "1995",
    > url = "citeseer.nj.nec.com/article/heckerman95tutorial.html" }
    >

    @article{ buntine96guide,
        author = "W. Buntine",
        title = "A guide to the literature on learning probabilistic networks from data",
        journal = "Ieee Trans. On Knowledge And Data Engineering",
        volume = "8",
        address = "Thinkbank, 1678 Shattuck Ave, Suite 320, Berkeley, Ca, 94709",
        pages = "195--210",
        year = "1996",
        url = "citeseer.nj.nec.com/buntine96guide.html" }

    I was also referred to:

    >
    > @book{Jor98,
    > author = "M. Jordan",
    > title = "Learning in Graphical Models",
    > publisher = "MIT Press",
    > address = "Cambridge",
    > year = "1998" }
    >
    > Hope this helps,

    This book contains the Heckerman tutorial, along with several other
    articles describing more recent research.

    I also discovered that

    \refrence{Cowell, R.G., A.P. Dawid, S.L. Lauritzen, and
    D.J. Spiegelhalter [1999]} {\it Probabilistic Networks and Expert
    Systems\/}. Springer.

    Has several chapters on learning issues towards the end of the book.

    Other suggestions I received:

    > @techreport{ buntine94learning,
    > author = "W. L. Buntine",
    > title = "Learning With Graphical Models",
    > number = "FIA-94-02",
    > address = "NASA Ames Research Center",
    > year = "1994",
    > url = "citeseer.nj.nec.com/article/buntine94learning.html" }
    >
    This may actually be:

    \refrence {Buntine, W.L. [1994]} ``Operations for Learning with
    Graphical Models.'' {\it Journal of Artificial Intelligence
    Research.\/} {\bf 2\/}, 159--225.

    > Zoubin's paper is specifically on learning dynamic
    > probabilistic models, and is well written and of
    > tutorial quality:
    >
    > @Article{Gha98,
    > author = "Z. Ghahramani",
    > title = "Learning Dynamic {Bayesian} Networks",
    > journal = "Lecture Notes in Computer Science",
    > volume = "1387",
    > pages = "168--198",
    > year = "1998",
    > coden = "LNCSD9",
    > ISSN = "0302-9743",
    > bibdate = "Sat Oct 10 14:40:24 MDT 1998",
    > acknowledgement = ack-nhfb,
    > }
    >
    > I have a very short survey paper
    > Rish, I.(2000). Advances in Bayesian Learning. Proceedings of the 2000
    > International Conference on Artificial Intelligence (IC-AI'2000). Las
    > Vegas,
    > you can find it on my web-page http://www.research.ibm.com/people/r/rish/
    > .

    > Another good paper by Heckerman et al.:
    >
    > @Article{HGC95,
    > author = "David Heckerman and Dan Geiger and David M.
    > Chickering",
    > title = "Learning {B}ayesian networks: the combination of
    > knowledge and statistical data",
    > journal = "Machine Learning",
    > volume = "20",
    > number = "3",
    > pages = "197--243",
    > year = "1995",
    > publisher = "Kluwer Academic Publishers, Boston",
    > }
    >
    >

    > You might also look for a copy of "Inference in Belief Networks: A
    > Procedural
    > Guide" by Cecil Huang and Adnan Darwiche from the International Journal of
    > Approximate Reasoning 1994 11:1-158
    >

    >
    > Paul Krause "Learning probabilistic networks" would be a good place to
    > start (if a little dated now).

    > it is NOT an article, and actually ment for non-computer scientists (or
    > statisticians), but you might
    > want to look at B-Course html-tutorial part for the data analysis service
    >
    > http://b-course.cs.helsinki.fi
    >
    > Although the data analysis service is state-of-the-art inside, we have
    > made an attempt to provide a very gentle introduction to the somewhat
    > hairy issue of real-life construction of Bayesian networks from data. I
    > understand that if you are looking for a good general scientific survey,
    > this "interactive introduction" is not what you need, but you might find
    > it useful anyway. B-Course is currently used by thousands of researchers
    > around the world and there will be a new release in two weeks (which
    > includes classification).

    Finally, I've attached the draft bibliography from the learning
    section of a tutorial on Graphical Models in Educational Assessment
    I'm currently working on.

    - --oVlSxhCMT8
    Content-Type: text/x-tex
    Content-Description: Draft bibliography for learning part of NCME tutorial
    Content-Disposition: inline;
            filename="learningBib.tex"
    Content-Transfer-Encoding: 7bit

    %% -*- mode: plain-tex; -*-
    %%**start of header
    \def\refrence#1{\par\hang\hskip-\parindent {\bf #1\/}.}
    %%**end of header

    \refrence {Andersen, S.A., Madiagn, D. and Perlman, M.D. [1996a]} ``A
    characterization of Markov equvilance classes for acyclic digraphs.''
    {\it Annals of Statistics,\/}, {\bf 25\/}, 505-41.

    \refernce {Andersen, S.A., Madigan, D. and Perlman, M.D. [1996b]} ``An
    Alternative Markov Property for Chain Graphs.'' {\it Uncertainty in
    Artificial Intelligence, Proceedings of the Twelfth Conference.\/}
    Morgan Kaufmann.

    \refrence {Buntine, W.L. [1994]} ``Operations for Learning with
    Graphical Models.'' {\it Journal of Artificial Intelligence
    Research,\/} {\bf 2\/}, 159--225.

    \refrence {Buntine, W.L. [1996]} ``A guide to the literature on
    learning probabilistic networks from data.'' {\it IEEE Trans. on
    Knowledge and Data Engineering,\/} {\bf 8\/}, 195--210.

    \refrence {Chickering, D. [1996]} ``Learning equivalence classes of
    Bayesian-network structures.'' {\it Proceedings of the Eleventh
    Conference on Uncertainty in Artificial Intelligence.\/} Morgan
    Kaufmann. 87--98.

    \refrence{Cooper, Gregory F. and Herskovits, Edward [1992]} ``A
    Bayesian Method for the Induction of Probabilistic Networks from
    Data.'' {\it Machine Learning\/} ({\bf 9\/}), 309--347.

    \refrence{Cowell, R.G., A.P. Dawid, S.L. Lauritzen, and
    D.J. Spiegelhalter [1999]} {\it Probabilistic Networks and Expert
    Systems\/}. Springer.

    \refrence {Dempster, A.P., Laird, N. and Rubin, D.B. [1972]} ``Maximum
    likelihood from incomplete data via the EM algorithm.'' {\it JRSS
    B\/}, {\bf 39\/}, 1--38.

    \refrence {Draper, David [1995]} ``Assessment and Propagation of Model
    Uncertainty.'' {\it JRSS B\/}, {\bf 57\/}, 45--98.

    \refrence{Draper, D., Hodges, J.S., Leamer, E.E., Morris, C.N. and
    Rubin, D.B. [1987]} ``A research agenda for assessment and
    propagation of model uncertainty.'' {Rand Note N-2683-RC}, The RAND
    Corporation, Santa Monica, California.

    \refrence {Heckerman, D. [1995]} ``A tutorial on learning with
    Bayesian networks.'' Technical Report MSR-TR-95-06, Microsoft
    Research, March, 1995 (revised November, 1996). (Reprinted in Jordan
    [1998]). {\tt ftp://ftp.research.microsoft.com/pub/tr/tr-95-06.pdf\/}

    \refrence {Heckerman, D., Gieger, D., and Chikering, D. [1995a]}
    ``Learning Bayesian networks: The combination of knowledge and
    statistical data.'' {\it Machine Learning,\/} {\bf 20,\/} 197--243.

    \refrence {Jaakkola, T.S. and Jordan, M.I. [1998]} ``Improving the
    Mean Field approximation via the use of Mixture Distrubutions.''
    In Jordan (ed) [1998] {\it Learning in Graphical Models.\/} Kulwer
    Academic Publishers. 163--173.

    \refrence {Jordan, M.I. (ed) [1998]} {\it Learning in Graphical
    Models.\/} Kulwer Academic Publishers. Reprinted by MIT Press.

    \refrence { Jordan, M.I., Ghahramani, Z., Jaakkola, T.S. and Saul,
    L.K. [1998]} ``An introduction to Variational Methods for Graphical
    Models.'' In Jordan (ed) [1998] {\it Learning in Graphical
    Models.\/} Kulwer Academic Publishers. 105--161.

    \refrence {Madigan, D. and A.E. Raftery [1994]} ``Model Selection
    and Accounting for Model Uncertainty in Graphical Models Using Occam's
    Window.'' {\it JASA\/}, {\bf 89\/}, 1535--1546.

    \refrence {Madigan, D., Raftery, A.E., Volinsky, C. and Hoeting,
    J. [1996]} ``Bayesian Model Averaging.'' {\it Proceedings of the AAI
    Workshop on Integrating Multiple Learned Models.\/}

    \refrence {Madigan, D., J. Gavrin and A.E. Raftery
    [1995]} ``Enhancing the Predictive Performance of Bayesian Graphical
    Models.'' {\it Communications in Statistics: Theory and Methods,\/}
    {\bf 24\/}, 2271--2292.

    \refrence{Meil\u a, M. and Jordan, M.I. [2000]} ``Learning with
    Mixtures of Trees.'' {\it Journal of Machine Learning Research\/},
    {\bf 1\/}, 1--48.

    \refrence {Rissanen, J. [1987]} ``Stochastic complexity (with
    discussion).'' {\it JRSS B,\/} {\bf 49\/}, 223--265.

    \refrence {Rubin, D.B. [1978]} ``Multiple imputation in sample surveys:
    A pheonomenological Bayesian approach to nonresponse.'' {\it
    Proceedings of the Survey Research Methods Section\/}, American
    Statistical Association, pp 20-44.

    \refrence {Schwarz, G. [1978]} ``Estimating the Dimension of a
    Model.'' {\it Annals of Statistics\/}, {\bf 6\/}, 461--464.

    \refrence {Shafer, G. [1996]} {\it The Art of Causal Conjecture.\/}
    MIT Press.

    \refrence {Spiegelhalter, D.J. and S.L. Lauritzen [1990]}
    ``Sequential Updating of Conditional Probabilities on Directed
     Graphical Structures.'' {\it Networks,\/} {\bf 20\/}, 579--605.

    \refrence {Spirtes, P., C. Meek and T.S. Richardson [1987]} ``A
     polynomial-time alogrithm for deteriming DAG equivalence in the
     presence of latent variables and selection bias.'' In Madigan and
     Smythe (eds) {\it Preliminary papers of the Sixth International
     Workshop on AI and Statistics\/}, 489--501.

    \refrence {Wermuth, N. and S.L. Lauritzen [1990]} `` On
    Substantive Research Hypotheses, Conditional Independence Graphs and
    Graphical Chain Models.'' {\it Journal of the Royal Statistical
    Society, Series B,\/} {\bf 52} 21--50.

    - --oVlSxhCMT8
    Content-Type: text/plain; charset=us-ascii
    Content-Description: message body text
    Content-Transfer-Encoding: 7bit

    My thanks to Daniel Nikovski, Irina Rish, Ben Perry, Andy Novobilski,
    Simon Parsons, Henry Tirri and Kristian Kersting for their
    suggestions.

            --Russell Almond



    This archive was generated by hypermail 2b29 : Tue Mar 19 2002 - 15:40:01 PST