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

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

The limits of MAP inference by MWSS on perfect graphs

Download to your calendar using vCal

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

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.

http://jmlr.org/proceedings/papers/v38/weller15.pdf

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

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Royal Institute of Philosophy - Annual Public Lectures - Anglia Ruskin University Pfeiffer Room, Hughes Hall, University of Cambridge Centre for Science and Policy Distinguished Lecture Series

Other talks

Fairy Tales Fairy Tales Discussion I In conversation: Louis Herns Marcelin and Ola Osman on legacies of enslavement and contemporary violence in Liberia and Haiti How Much Does Homology Really Know? Zooming in on the assembly of galaxies in the early Universe
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity