=========================================================================

Learning on Cores, Clusters, and Clouds
NIPS 2010 Workshop, Whistler, British Columbia, Canada

http://lccc.eecs.berkeley.edu/

-- Submission Deadline: October 17, 2010 --

=========================================================================

In the current era of web-scale datasets, high throughput biology, and multilanguage machine translation, modern datasets no longer fit on a single computer and traditional machine learning algorithms often have prohibitively long running times. Parallel and distributed machine learning is no longer a luxury; it has become a necessity. Moreover, industry leaders have already declared that clouds are the future of computing, and new computing platforms such as Microsoft's Azure and Amazon's EC2 are bringing distributed computing to the masses.

The machine learning community is reacting to this trend in computing by developing new parallel and distributed machine learning techniques. However, many important challenges remain unaddressed. Practical distributed learning algorithms must deal with limited network resources, node failures and nonuniform network latencies. In cloud environments, where network latencies are especially large, distributed learning algorithms should take advantage of asynchronous updates.

Many similar issues have been addressed in other fields, where distributed computation is more mature, such as convex optimization and numerical computation. We can learn from their successes and their failures.

The one day workshop on "Learning on Cores, Clusters, and Clouds" aims to bring together experts in the field and curious newcomers, to present the state-of-the-art in applied and theoretical distributed learning, and to map out the challenges ahead. The workshop will include invited and contributed presentations from leaders in distributed learning and adjacent fields.

We would like to invite short high-quality submissions on the following topics:

* Distributed algorithms for online and batch learning
* Parallel (multicore) algorithms for online and batch learning
* Computational models and theoretical analysis of distributed and parallel learning
* Communication avoiding algorithms
* Learning algorithms that are robust to hardware failures
* Experimental results and interesting applications

Interesting submissions in other relevant topics not listed above are welcome too. Due to the time constraints, most accepted submissions will be presented as poster spotlights.

Submission guidelines:

Submissions should be written as extended abstracts, no longer than 4 pages in the NIPS latex style. NIPS style files and formatting instructions can be found at http://nips.cc/PaperInformation/StyleFiles (although we will not enforce the double blind part). The extended abstract may be accompanied by an unlimited appendix and other supplementary material, with the understanding that anything beyond 4 pages may be ignored by the program committee. Please send your submission by email to submit.lccc@gmail.com before October 17 at midnight PST. Notifications will be given on or before Nov 7. Topics that were recently published or presented elsewhere are allowed, provided that the extended abstract mentions this explicitly; topics that were presented in non-machine-learning conferences are especially encouraged.

Organizers:

Alekh Agarwal (UC Berkeley), Ofer Dekel (Microsoft), John Duchi (UC Berkeley), John Langford (Yahoo!)

Program Committee:

Ron Bekkerman (LinkedIn), Misha Bilenko (Microsoft), Ran Gilad-Bachrach (Microsoft), Guy Lebanon (Georgia Tech), Ilan Lobel (NYU), Gideon Mann (Google), Ryan McDonald (Google), Ohad Shamir (Microsoft), Alex Smola (Yahoo!), S V N Vishwanathan (Purdue), Martin Wainwright (UC Berkeley), Lin Xiao (Microsoft)