Talks and Poster Presentations (with Proceedings-Entry):
J. Jancsary, G. Matz:
"Convergent decomposition solvers for tree-reweighted free energies";
Talk: International Conference on Artificial Intelligence and Statistics,
Fort Lauderdale, Florida (USA);
- 04-13-2011; in: "Proc. AISTATS'11",
We investigate minimization of tree- reweighted free energies for the purpose of obtaining approximate marginal probabil- ities and upper bounds on the partition function of cyclic graphical models. The solvers we present for this problem work by directly tightening tree-reweighted upper bounds. As a result, they are particularly efficient for tree-reweighted energies arising from a small number of spanning trees. While this assumption may seem restrictive at first, we show how small sets of trees can be constructed in a principled manner. An appealing property of our algorithms, which results from the problem decomposition, is that they are embarrassingly parallel. In contrast to the original message passing algorithm introduced for this problem, we obtain global convergence guarantees.
Electronic version of the publication:
Created from the Publication Database of the Vienna University of Technology.