OPT 2010 - OPT 2010 3rd International Workshop on Optimization for Machine Learning

OPT 2010

3rd International Workshop on Optimization for Machine Learning

NIPS*2010 Workshop

December 10th, 2010, Whistler, Canada

URL: http://opt.kyb.tuebingen.mpg.de/


Abstract


Optimization is a well-established, mature discipline. But the way we use
this discipline is undergoing a rapid transformation: the advent of modern
data intensive applications in statistics, scientific computing, or data
mining and machine learning, is forcing us to drop theoretically powerful
methods in favor of simpler but more scalable ones. This changeover exhibits
itself most starkly in machine learning, where we have to often process
massive datasets; this necessitates not only reliance on large-scale
optimization techniques, but also the need to develop methods "tuned" to the
specific needs of machine learning problems.

Background and Objectives


We build on OPT*2008 and 2009, the forerunners to this workshop that happened
as a part of NIPS workshops. Beyond that significant precedent, there have
been several other related workshops such as the "Mathematical Programming in
Machine Learning / Data Mining" series (2005 to 2007) and the BigML NIPS 2007
workshop.

Our workshop has the following major aims:

* Provide a platform for increasing the interaction between researchers from

optimization, operations research, statistics, scientific computing, and

machine learning;

* Identify key problems and challenges that lie at the intersection of

optimization and ML;

* Narrow the gap between optimization and ML, to help reduce rediscovery,

and thereby accelerate new advances.

Call for Participation


This year we invite two types of submissions to the workshop:

(i) contributed talks and/or posters

(ii) open problems

For the latter, we request the authors to prepare a few slides that clearly
present, motivate, and explain an important open problem --- the main aim here
is to foster active discussion. The topics of interest for the open
problem session are the same as those for regular submissions; please see
below for details.

In addition to open problems, we invite high quality submissions for
presentation as talks or poster presentations during the workshop. We are
especially interested in participants who can contribute theory / algorithms,
applications, or implementations with a machine learning focus on the
following topics:

Topics


* Stochastic, Parallel and Online Optimization,

- Large-scale learning, massive data sets

- Distributed algorithms

- Optimization on massively parallel architectures

- Optimization using GPUs, Streaming algorithms

- Decomposition for large-scale, message-passing and online learning

- Stochastic approximation

- Randomized algorithms

* Algorithms and Techniques (application oriented)

- Global and Lipschitz optimization

- Algorithms for non-smooth optimization

- Linear and higher-order relaxations

- Polyhedral combinatorics applications to ML problems

* Non-Convex Optimization,

- Non-convex quadratic programming, including binary QPs

- Convex Concave Decompositions, D.C. Programming, EM

- Training of deep architectures and large hidden variable models

- Approximation Algorithms

* Optimization with Sparsity constraints

- Combinatorial methods for L0 norm minimization

- L1, Lasso, Group Lasso, sparse PCA, sparse Gaussians

- Rank minimization methods

- Feature and subspace selection

* Combinatorial Optimization

- Optimization in Graphical Models

- Structure learning

- MAP estimation in continuous and discrete random fields

- Clustering and graph-partitioning

- Semi-supervised and multiple-instance learning

Important Dates


* Deadline for submission of papers: 24st October 2010

* Notification of acceptance: 12th November 2010

* Final version of submission: 20th November 2010

* Workshop date: 10th December 2010

Please note that at least one author of each accepted paper must be available
to present the paper at the workshop. Further details regarding the
submission process are available at the workshop homepage (style files, page
limits, etc.)

Workshop


The workshop will be a one-day event with a morning and afternoon session. In
addition to a lunch break, long coffee breaks will be offered both in the
morning and afternoon.

A new session on open problems is proposed for spurring active discussion and
interaction amongst the participants. A key aim of this session will be on
establishing areas and problems of interest to the community.

Invited Speakers


* Yurii Nesterov -- Catholic University of Louvain

* Laurent El Ghaoui -- University of California, Berkeley

* Mark Schmidt -- University of British Columbia

Workshop Organizers


* Suvrit Sra, Max Planck Institute for Biological Cybernetics

* Sebastian Nowozin, Microsoft Research, Cambridge, UK

* Stephen Wright, University of Wisconsin, Madison