Team for Research in
Ubiquitous Secure Technology

Citation
Venkat Chandrasekaran, Jason K. Johnson, Alan S. Willsky. "Maximum Entropy Relaxation for Graphical Model Selection given Inconsistent Statistics". IEEE Statistical Signal Processing Workshop, August, 2007.

Abstract
We develop a novel approach to approximate a specified collection of marginal distributions on subsets of variables by a globally consistent distribution on the entire collection of variables. In general, the specified marginal distributions may be inconsistent on overlapping subsets of variables. Our method is based on maximizing entropy over an exponential family of graphical models, subject to divergence constraints on small subsets of variables that enforce closeness to the specified marginals. The resulting optimization problem is convex, and can be solved efficiently using a primal-dual interior-point algorithm. Moreover, this framework leads naturally to a solution that is a sparse graphical model.

Electronic downloads

• cjw_mer_ssp07.pdf · application/pdf · 388 kbytes

• HTML

  Venkat Chandrasekaran, Jason K. Johnson, Alan S. Willsky.
  <a href="http://www.truststc.org/pubs/268.html"
  >Maximum Entropy Relaxation for Graphical Model Selection
  given Inconsistent Statistics</a>, IEEE Statistical
  Signal Processing Workshop, August, 2007.

• Plain text

  Venkat Chandrasekaran, Jason K. Johnson, Alan S. Willsky.
  "Maximum Entropy Relaxation for Graphical Model
  Selection given Inconsistent Statistics". IEEE
  Statistical Signal Processing Workshop, August, 2007.

• BibTeX

  @inproceedings{ChandrasekaranJohnsonWillsky07_MaximumEntropyRelaxationForGraphicalModelSelectionGiven,
      author = {Venkat Chandrasekaran and Jason K. Johnson and
                Alan S. Willsky},
      title = {Maximum Entropy Relaxation for Graphical Model
                Selection given Inconsistent Statistics},
      booktitle = {IEEE Statistical Signal Processing Workshop},
      month = {August},
      year = {2007},
      abstract = {We develop a novel approach to approximate a
                specified collection of marginal distributions on
                subsets of variables by a globally consistent
                distribution on the entire collection of
                variables. In general, the specified marginal
                distributions may be inconsistent on overlapping
                subsets of variables. Our method is based on
                maximizing entropy over an exponential family of
                graphical models, subject to divergence
                constraints on small subsets of variables that
                enforce closeness to the specified marginals. The
                resulting optimization problem is convex, and can
                be solved efficiently using a primal-dual
                interior-point algorithm. Moreover, this framework
                leads naturally to a solution that is a sparse
                graphical model.},
      URL = {http://www.truststc.org/pubs/268.html}
  }
  

Posted by Venkat Chandrasekaran on 21 Jul 2007.
For additional information, see the Publications FAQ or contact webmaster at www truststc org.