IEEE Signal Processing Magazine Special Issue on: Dimensionality Reduction via Subspace and Manifold Learning

IEEE Signal Processing Magazine Special Issue on:
Dimensionality Reduction via Subspace and Manifold Learning

Call For Whitepapers

Scope and Purpose:

The problem of finding and exploiting low-dimensional structures in high-dimensional data is taking on increasing importance in image, video, or audio processing, web data analysis/search, and bioinformatics, where datasets now routinely lie in thousands to millions-dimensional observation spaces. The curse of dimensionality is in full play here: We often need to conduct meaningful inference with limited number of samples in a very high-dimensional space. Conventional statistical and computational tools are often severely inadequate for processing and analyzing high-dimensional data. Although the data might be presented in a high-dimensional space, their intrinsic complexity and local dimensions are typically much lower.

This special issue of IEEE Signal Processing Magazine is to attract articles that cover existing approaches to dimension reduction based on learning of subspaces or submanifolds -- from linear to nonlinear models, from homogeneous to hybrid models, from statistical, to geometric, to algebraic, and to graphical methods. We would also like to feature many successful applications of these new methods, including but not limited to signal/image processing, pattern recognition, bioinformatics, and web data mining. Below is an incomplete list of potential topics to be covered in the special issue:

Kernel PCA and Robust PCA with Incomplete and Corrupted Data
Generalized PCA and Subspace Arrangements
Manifold Learning and Dimension Reduction
Learning of Stratification and Submanifold Arrangements
Spectral Methods for Data Clustering and Manifold Learning
Source Separation Based on Subspace Models
Dictionary Learning for Sparse Representation
Algebraic, Geometric, and Topological Methods for Manifold Learning and Clustering

Signal/Image Processing Applications of Subspace Analysis, Manifold Learning, and Dimension Reduction

Important Dates (whitepaper submission time postponed!):

Whitepaper due: November 15, 2009.
Invitation notification: December 15, 2009.
Manuscript due: April 1, 2010.
Acceptance notification: July 1, 2010.
Final manuscript due: August 1, 2010.
Anticipated publication: November, 2010.

Whitepaper and Manuscript Submission Guidelines:

Submissions to this special issue must follow a two-stage process. First, a 2-page whitepaper is submitted. Whitepapers will be reviewed and assessed by the editors based on their quality and relevance to this special issue. Invitations for full papers will be sent out to authors of qualified whitepapers. The submitted papers will still undergo independent, blind peer review for final selection.

Prospective authors should submit their whitepapers (maximum 2 pages, single column, fonts >= 10pt) to the web submission system through IEEE Manuscript Central at: http://mc.manuscriptcentral.com/spmag-ieee.

NOTICE: For early submitters, the submission site might still be under test for now and should be available soon. So please make sure you (re)submit your whitepaper after the site goes online officially. We apologize if this has caused you any trouble.

Guest Editors:

Guest Chief Editor:

Professor Yi Ma, Electrical and Computer Engineering, University of Illinois at Urbana-Champaign.

Guest Associate Editors:

Professor Partha Niyogi Computer Sciences, Statistics, University of Chicago.
Professor Guillermo Sapiro, Electrical and Computer Engineering, University of Minnesota.
Professor Rene Vidal, Biomedical Engineering, Computer Science, Johns Hopkins University.

All manuscripts will undergo independent, blind peer reviews, administered by all the editors. Acceptance will be based on the quality of the paper and its relevance to the special issue. If you have specific questions about the review and decision of your manuscript, please contact the Chief Editor, Prof. Yi Ma: yima@uiuc.edu.