[Ml-stat-talks] Fwd: [talks] Colloquium Speaker: Stefanie Jegelka Tues April 8th 4:30pm

David Blei blei at CS.Princeton.EDU
Mon Apr 7 14:51:34 EDT 2014

dear ml-stat-talks

tomorrow's CS colloquium will be very interesting.  see below.


---------- Forwarded message ----------
From: Nicole E. Wagenblast <nwagenbl at cs.princeton.edu>
Date: Mon, Apr 7, 2014 at 8:55 AM
Subject: [talks] Colloquium Speaker: Stefanie Jegelka Tues April 8th 4:30pm
To: "Talks (colloquium)" <talks at lists.cs.princeton.edu>

Efficient learning with combinatorial structure Stefanie
University of California, Berkeley <https://amplab.cs.berkeley.edu/>
Tuesday, April 8, 4:30pm
Computer Science 105

Learning from complex data such as images, text or biological measurements
invariably relies on capturing long-range, latent structure. But the
combinatorial structure inherent in real-world data can pose significant
computational challenges for modeling, learning and inference.

In this talk, I will view these challenges through the lens of submodular
set functions. Considered a "discrete analog of convexity", the
combinatorial concept of submodularity captures intuitive yet nontrivial
dependencies between variables and underlies many widely used concepts in
machine learning. Practical use of submodularity, however, requires care.
My first example illustrates how to efficiently handle the important class
of submodular composite models. The second example combines submodularity
and graphs for a new family of combinatorial models that express long-range
interactions while still admitting very efficient inference procedures. As
a concrete application, our results enable effective realization of
combinatorial sparsity priors on real data, significantly improving image
segmentation results in settings where state-of-the-art methods
fail. Motivated by good empirical results, we provide a detailed
theoretical analysis and identify practically relevant properties that
affect complexity and approximation quality of submodular optimization and
learning problems.

Stefanie Jegelka is a postdoctoral researcher at UC Berkeley, working with
Michael I. Jordan and Trevor Darrell. She received a Ph.D. in Computer
Science from ETH Zurich in 2012, in collaboration with the Max Planck
Institute for Intelligent Systems, and completed her studies for a Diploma
in Bioinformatics with distinction at the University of Tuebingen (Germany)
and the University of Texas at Austin. She was a fellow of the German
National Academic Foundation (Studienstiftung) and its scientific college
for life sciences, and has received a Google Anita Borg Europe Fellowship
and an ICML Best Paper Award. She has also been a research visitor at
Georgetown University Medical Center and Microsoft Research and has held
workshops and tutorials on submodularity in machine learning.

talks mailing list
talks at lists.cs.princeton.edu
To edit subscription settings or remove yourself, use this link:
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20140407/5dc92840/attachment.html>

More information about the Ml-stat-talks mailing list