CALL FOR PAPERS
Low-rank Matrix Approximation for Large-scale Learning
NIPS 2010 Workshop, Whistler, Canada
December 11, 2010
Submission Deadline: October 31, 2010
Today’s data-driven society is full of large-scale datasets. In the context of machine learning,
these datasets are often represented by large matrices representing either a set of real-valued
features for each point or pairwise similarities between points. Hence, modern learning
problems in computer vision, natural language processing, computational biology, and other
areas often face the daunting task of storing and operating on matrices with thousands to
millions of entries. An attractive solution to this problem involves working with low-rank
approximations of the original matrix. Low-rank approximation is at the core of widely used
algorithms such as Principle Component Analysis, Multidimensional Scaling, Latent Semantic
Indexing, and manifold learning. Furthermore, low-rank matrices appear in a wide variety of
applications including lossy data compression, collaborative filtering, image processing, text
analysis, matrix completion and metric learning.
The NIPS workshop on “Low-rank Matrix Approximation for Large-scale Learning” aims to
survey recent work on matrix approximation with an emphasis on usefulness for practical
large-scale machine learning problems. We aim to provide a forum for researchers to discuss
several important questions associated with low-rank approximation techniques.
The workshop will begin with an introductory talk and will include invited talks by
Emmanuel Candes (Stanford), Ken Clarkson (IBM
Almaden) and Petros Drineas (RPI). There will also be several contributed paper talks as well
as poster session for contributed papers.
We encourage submissions exploring the impact of low-rank methods for large-scale machine
learning in the form of new algorithms, theoretical advances and/or empirical results. We also
welcome work on related topics that motivate additional interesting scenarios for use of low-
rank approximations for learning tasks. Some specific areas of interest include randomized
low-rank approximation techniques, the effect of data heterogeneity on randomization,
performance of various low-rank methods for large-scale tasks and the tradeoff between
numerical precision and time/space efficiency in the context of machine learning
performance, e.g., classification or clustering accuracy.
Submissions should be written as extended abstracts, no longer than 4 pages in the NIPS
latex style. Style files and formatting instructions can be found at
Submisssions must be in PDF format. Authors names and affiliations should be included, as
the review process will not be double blind.
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 PDF submission by email to firstname.lastname@example.org by October 31.
Notifications will be given on or before November 15.
Topics that were recently published or presented elsewhere are allowed, provided that the
extended abstract mentions this explicitly.
Michael Mahoney (Stanford), Mehryar Mohri (NYU, Google Research), Ameet Talwalkar
Alexandre d’Aspremont (Princeton), Christos Boutsidis (Rensselear Polytechnic Institute),
Kamilika Das (NASA Ames Research Center), Maryam Fazel (Washington), Michael I.
Jordan (Berkeley), Sanjiv Kumar (Google Research), James Kwok (Hong Kong University of
Science and Technology), Gunnar Martinsson (Colorado at Boulder)