University of Cambridge > > Machine Learning @ CUED > The limits of MAP inference by MWSS on perfect graphs

The limits of MAP inference by MWSS on perfect graphs

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact dsu21.

I shall briefly describe a recent, promising method to perform MAP inference for discrete undirected graphical models based on reducing the optimization problem to finding a maximum weight stable set (MWSS) in a derived weighted graph, which if perfect, may be performed in time polynomial in the number of variables. I shall discuss recent work (AISTATS 2015), where the limits of this approach were established for the class of binary pairwise (Ising) models, yielding a simple, interesting characterization.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity