<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=utf-8">
</head>
<body bgcolor="#FFFFFF" text="#000000">
[Apologies for cross posting.]<br>
<br>
==========================================<br>
<font size="+1">Call for papers and participation : <i>Greed is
Great<br>
</i>held in conjunction with ICML 2015 <i><br>
</i><br>
Friday, July 10, 2015, Lille, France<br>
<br>
<a class="moz-txt-link-freetext"
href="https://sites.google.com/site/gretaproject/greed-is-great-icml">https://sites.google.com/site/gretaproject/greed-is-great-icml</a><br>
=====================================<br>
</font><br>
Overview<br>
------------<br>
<br>
Over the past few years, many problems from machine learning and
signal processing have aimed at automatically learning sparse
representations from data and a very popular strategy has been to
state the mentioned problems as convex optimization problems.
However, aiming at sparsity actually involves an ℓ0 "norm"
regularization/constraint, and the convex optimization way is
essentially a proxy to induce sparsity—through, e.g., the recourse
to an ℓ1 norm, which itself is a proxy to ℓ0. <br>
<br>
Greedy methods constitute another strategy to tackle the
combinatorial optimization problems posed by the issue of learning
sparse representations/predictors. Yet, this family of methods has
been much less investigated than the convex relaxation approach by
the ICML community. This is precisely the purpose of this workshop
to give a central place to greedy methods for machine learning and
discuss the blessings of such methods from the computational and
generalization perspectives. <br>
<br>
The program of this workshop will critically build upon a) the
wealth of work on greedy algorithms in fields of theoretical
computer science such as discrete algorithms or graph theory and b)
the existence of machine learning, signal processing, and
statistical modeling contributions that show it is possible to take
advantage of properties of greedy algorithms that go beyond their
mere computational merits. As such, the topics of interest include,
but are not limited to :<br>
<br>
- (kernel) matching pursuit procedures and variants,<br>
- matroid theory,<br>
- submodular optimization,<br>
- greedy (discrete) optimization,<br>
- spark, coherence, exact recovery,<br>
- compressed sensing.<br>
<br>
Format and submissions<br>
------------------------------<br>
<br>
The contributions should come in the form of short papers, not
exceeding 4 page, references excluded, and should be formatted as
per the main conference guidelines, available at <a
class="moz-txt-link-freetext"
href="http://icml.cc/2015/?page_id=151">http://icml.cc/2015/?page_id=151</a>.
The papers should include authors names and affiliation. We also
welcome papers that have been accepted in recent editions of machine
learning and signal processing conferences and journals, such as
ICML (including the current edition), NIPS, ECML, ALT and COLT. All
the accepted papers will be featured in the poster sessions and a
selected few will also be presented as contributed talks and
featured in spotlight sessions. Submissions should be made via
e-mail at <a class="moz-txt-link-abbreviated"
href="mailto:googlegreedisgreatICML2015@gmail.com">googlegreedisgreatICML2015@gmail.com</a>.
<br>
<br>
Important dates<br>
---------------------<br>
<br>
Submission deadline: May 1, 2015<br>
Notification of acceptance: May 10, 2015<br>
Camera-ready: May 24, 2015<br>
<br>
<br>
On behalf of Project GRETA People<br>
<br>
</body>
</html>