HPL-2009-67On semi-supervised learning and sparsity
Balinsky, Alexander; Balinsky, Helen
Keyword(s): semi-supervised learning, compressive sampling, sparsity of filter response
Abstract: In this article we establish a connection between semi-supervised learning and compressive sampling. We show that sparsity and compressibility of the learning function can be obtained from heavy-tailed distributions of filter responses or coefficients in spectral decompositions. In many cases the NP-hard problems of finding sparsest solutions can be replaced by l1-problems from convex optimisation theory, which provide effective tools for semi-supervised learning. We present several conjectures and examples.
Additional Publication Information: To be published and presented at 2009 IEEE International Conference on Systems, Man, and Cybernetics, October 11-14, 2009, San Antonio, Texas, USA
External Posting Date: August 21, 2009 [Abstract Only]. Approved for External Publication - External Copyright Consideration
Internal Posting Date: August 21, 2009 [Fulltext]