Friday, August 30, 2013

[DMANET] NIPS 2013 Workshop on Greedy Algorithms, Frank-Wolfe and Friends - Call for Contributions

We invite contributions to the first

International Workshop on
Greedy Algorithms, Frank-Wolfe and Friends - A modern perspective,
to be held as a part of the
26th Annual Conference on Neural Information Processing Systems
(NIPS 2013),
December 9 or 10, 2013, Lake Tahoe, Nevada, USA.

Website: http://sites.google.com/site/nips13greedyfrankwolfe/

Submission Deadline: 16th October 2013
__________________________________


The exciting program includes plenary talks by:

Francis Bach, ENS and INRIA, Paris
Arkadi Nemirovski, Georgia Tech (TBC)
Benjamin Recht, UC Berkeley
Shai Shalev-Shwartz, Hebrew University Jerusalem
Vladimir Temlyakov, University of South Carolina


Overview
-------------

Greedy algorithms and projection-free first-order optimization
algorithms are at the core of many of the state of the art sparse
methods in machine learning, signal processing, harmonic analysis,
statistics and other seemingly unrelated areas, with different goals
at first sight. Examples include matching pursuit, boosting, greedy
methods for sub-modular optimization, with applications ranging from
large-scale structured prediction to recommender systems. In the field
of optimization, the recent renewed interest in
Frank-Wolfe/conditional gradient algorithms opens up an interesting
perspective towards a unified understanding of these methods, with a
big potential to translate the rich existing knowledge about the
respective greedy methods between the different fields.

The goal of this workshop is to take a step towards building a modern
and consistent perspective on these related algorithms. The workshop
will gather renowned experts working on those algorithms in machine
learning, optimization, signal processing, statistics and harmonic
analysis, in order to engender a fruitful exchange of ideas and
discussions and to push further the boundaries of scalable and
efficient optimization for learning problems.


Scope
--------------
The main topics are, including, but not limited to:

* Convex Optimization
- Sparse greedy methods
- Sparse first and second order optimization
- Frank-Wolfe / conditional gradient type methods
- Extensions to non-smooth or special problem classes
- Acceleration techniques
- Theoretical convergence rates

* Sparse Methods in Signal Processing
- Atomic decompositions
- Matching pursuit and OMP
- Forward / backward selection methods
- Sparse recovery algorithms

* Statistics and Machine Learning
- Boosting methods
- Graphical model selection
- Sparse methods

* Linear algebra and Matrix analysis
- Matrix and tensor factorizations
- Sparse and low-rank matrix optimization problems

* Harmonic Analysis
- Greedy methods
- Sparse approximation

* Applications
- Empirical comparisons and applications of related methods

Special focus will be given to papers tackling "big data" problems.


Submission
------------------

We encourage attendees for contribution of an extended abstract (up to
4 pages using NIPS style). Abstracts should be sent via EasyChair
https://www.easychair.org/conferences/?conf=greedy2013
Accepted submissions will be presented as short talks or posters.

Important Dates
-------------------------

October 16 - Deadline for submission
October 30 - Notification of acceptance
December 9 or 10 (TBD) - Workshop day

Organizers
----------------

Zaid Harchaoui, INRIA Grenoble (France)
Martin Jaggi, Simons Institute, Berkeley (USA)
Federico Pierucci, LJK lab, Grenoble (France)

If you have any questions or comments please send an e-mail to
nips.greedy.2013@gmail.com

Website
---------------

http://sites.google.com/site/nips13greedyfrankwolfe/
**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************