######################################################################

CALL FOR PAPERS

Coarse-to-Fine Learning and Inference

a workshop in conjunction with

24th Annual Conference on Neural Information Processing Systems (NIPS 2010)

December 10 or 11, 2010 Whistler, BC, Canada

http://learning.cis.upenn.edu/coarse2fine/

Deadline for Submissions: Friday, October 29, 2010
Notification of Decision: Monday, November 8, 2010

#####################################################################

Overview

The bottleneck in many complex prediction problems is the prohibitive
cost of inference or search at test time. Examples include structured
problems such as object detection and segmentation, natural language
parsing and translation, as well as standard classification with
kernelized or costly features or a very large number of classes. These
problems present a fundamental trade-off between approximation error
(bias) and inference or search error due to computational constraints
as we consider models of increasing complexity. This trade-off is much
less understood than the traditional approximation/estimation
(bias/variance) trade-off but is constantly encountered in machine
learning applications. The primary aim of this workshop is to formally
explore this trade-off and to unify a variety of recent approaches,
which can be broadly described as "coarse-to-fine" methods, that
explicitly learn to control this trade-off. Unlike approximate
inference algorithms, coarse-to-fine methods typically involve exact
inference in a coarsened or reduced output space that is then
iteratively refined. They have been used with great success in
specific applications in computer vision (e.g., face detection) and
natural language processing (e.g., parsing, machine translation).
However, coarse-to-fine methods have not been studied and formalized
as a general machine learning problem. Thus many natural theoretical
and empirical questions have remained un-posed; e.g., when will such
methods succeed, what is the fundamental theory linking these
applications, and what formal guarantees can be found?

A significant portion of the workshop will be given over to
discussion, in the form of two organized panel discussions and a small
poster session. We have taken care to invite speakers who come from
each of the research areas mentioned above, and we intend to similarly
ensure that the panels are comprised of speakers from multiple
communities. We anticipate that this workshop will lead to new
research directions in the analysis and development of coarse-to-fine
and other methods that address the bias/computation trade-off,
including the establishment of several benchmark problems to allow
easier entry by researchers who are not domain experts into this area.
Call for Participation

We invite submission of workshop papers that discuss ongoing or
completed work in machine learning, computer vision, and natural
language processing and addressing large-scale prediction problems
where inference cost is a major bottleneck. Furthermore, because the
"coarse-to-fine" label is broadly interpreted across many different
fields, we also invite any submission that involves learning to
address the bias/computation trade-off or that provides new
theoretical insight into this problem. A workshop paper should be no
more than six pages in the standard NIPS format. Authorship should not
be blind. Please submit a paper by emailing it in Postscript or PDF
format to coarse2fineNIPS2010@gmail.com. We anticipate accepting six
such papers for poster presentations, some of which will also receive
an oral presentation. Please only submit an article if at least one of
the authors will be able to attend the workshop and present the work.

* Please use NIPS template and style files. No more than 6 pages,
authorship not blind.
* Submit to coarse2fineNIPS2010@gmail.com by October 29.

Important Dates:

* Friday, October 29 -- Paper submission deadline
* Monday, November 8 -- Notification of acceptance

Organizers:

Ben Taskar taskar@cis.upenn.edu University of Pennsylvania
David Weiss djweiss@cis.upenn.edu University of Pennsylvania
Ben Sapp bensapp@cis.upenn.edu University of Pennsylvania
Slav Petrov petrov@cs.berkeley.edu Google Research, New York