Finding needles in compressed haystacks

Journal Article

In this paper, we investigate the problem of compressed learning, i.e. learning directly in the compressed domain. In particular, we provide tight bounds demonstrating that the linear kernel SVMs classifier in the measurement domain, with high probability, has true accuracy close to the accuracy of the best linear threshold classifier in the data domain. Furthermore, we indicate that for a family of well-known deterministic compressed sensing matrices, compressed learning is provided on the fly. Finally, we support our claims with experimental results in the texture analysis application. © 2012 IEEE.

Full Text

Duke Authors

Cited Authors

  • Calderbank, R; Jafarpour, S

Published Date

  • October 23, 2012

Published In

Start / End Page

  • 3441 - 3444

International Standard Serial Number (ISSN)

  • 1520-6149

Digital Object Identifier (DOI)

  • 10.1109/ICASSP.2012.6288656

Citation Source

  • Scopus