[Ml-stat-talks] Fwd: [talks] Colloquium Speaker, Mon April 19th- David Sontag

David Blei david.blei at gmail.com
Thu Apr 15 16:34:45 EDT 2010

hi ml-stat-talks

do not miss david sontag next monday 4/19 at 4:30PM.  he will discuss
his work on approximate inference in graphical models and its
connection to optimization.  it promises to be a great talk.  see the
details below.


---------- Forwarded message ----------
From: Nicole E. Wagenblast <nwagenbl at cs.princeton.edu>
Date: Thu, Apr 15, 2010 at 4:30 PM
Subject: [talks] Colloquium Speaker, Mon April 19th- David Sontag
To: "Talks (colloquium)" <talks at lists.cs.princeton.edu>

Approximate Inference in Graphical Models using LP Relaxations
David Sontag, MIT
Monday, April 19th, 2010- 4:30pm
Computer Science, Small Auditorium CS105

Graphical models such as Markov random fields have been successfully
applied to a wide variety of fields, from computer vision and natural
language processing, to computational biology. Exact probabilistic
inference is generally intractable in complex models having many
dependencies between the variables.

In this talk, I will discuss recent work on using linear programming
relaxations to perform approximate inference. By solving the LP
relaxations in the dual, we obtain efficient message-passing
algorithms that, when the relaxations are tight, can provably find the
most likely (MAP) configuration.

Our algorithms succeed at finding the MAP configuration in protein
side-chain placement, protein design, and stereo vision problems. More
broadly, this talk will highlight emerging connections between machine
learning, polyhedral combinatorics, and combinatorial optimization.
talks mailing list
talks at lists.cs.princeton.edu

More information about the Ml-stat-talks mailing list