Advanced Search

An Equivalence Between Sparse Approximation and Support Vector Machines

Research and Teaching Output of the MIT Community

Show simple item record Girosi, Federico en_US 2004-10-22T20:17:52Z 2004-10-22T20:17:52Z 1997-05-01 en_US
dc.identifier.other AIM-1606 en_US
dc.identifier.other CBCL-147 en_US
dc.description.abstract In the first part of this paper we show a similarity between the principle of Structural Risk Minimization Principle (SRM) (Vapnik, 1982) and the idea of Sparse Approximation, as defined in (Chen, Donoho and Saunders, 1995) and Olshausen and Field (1996). Then we focus on two specific (approximate) implementations of SRM and Sparse Approximation, which have been used to solve the problem of function approximation. For SRM we consider the Support Vector Machine technique proposed by V. Vapnik and his team at AT&T Bell Labs, and for Sparse Approximation we consider a modification of the Basis Pursuit De-Noising algorithm proposed by Chen, Donoho and Saunders (1995). We show that, under certain conditions, these two techniques are equivalent: they give the same solution and they require the solution of the same quadratic programming problem. en_US
dc.format.extent 16 p. en_US
dc.format.extent 305230 bytes
dc.format.extent 497486 bytes
dc.format.mimetype application/postscript
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.relation.ispartofseries AIM-1606 en_US
dc.relation.ispartofseries CBCL-147 en_US
dc.subject Support Vector Machines en_US
dc.subject Sparse Approximation en_US
dc.subject Sparse Coding en_US
dc.subject Reproducing Kernel Hilbert Spaces en_US
dc.title An Equivalence Between Sparse Approximation and Support Vector Machines en_US

Files in this item

Name Size Format Description 298.0Kb Postscript
AIM-1606.pdf 485.8Kb PDF

This item appears in the following Collection(s)

Show simple item record