Information-theoretic criteria for the design of compressive subspace classifiers
Publication
, Journal Article
Nokleby, M; Rodrigues, M; Calderbank, R
Published in: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
January 1, 2014
Using Shannon theory, we derive fundamental, asymptotic limits on the classification of low-dimensional subspaces from compressive measurements. We identify a syntactic equivalence between the classification of subspaces and the communication of codewords over non-coherent, multiple-antenna channels, from which we derive sharp bounds on the number of classes that can be discriminated with low misclassification probability as a function of the signal dimensionality and the signal-to-noise ratio. While the bounds are asymptotic in the limit of high dimension, they provide intuition for classifier design at finite dimension. We validate this intuition via an application to face recognition. © 2014 IEEE.
Duke Scholars
Published In
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
DOI
ISSN
1520-6149
Publication Date
January 1, 2014
Start / End Page
3067 / 3071
Citation
APA
Chicago
ICMJE
MLA
NLM
Nokleby, M., Rodrigues, M., & Calderbank, R. (2014). Information-theoretic criteria for the design of compressive subspace classifiers. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 3067–3071. https://doi.org/10.1109/ICASSP.2014.6854164
Nokleby, M., M. Rodrigues, and R. Calderbank. “Information-theoretic criteria for the design of compressive subspace classifiers.” ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, January 1, 2014, 3067–71. https://doi.org/10.1109/ICASSP.2014.6854164.
Nokleby M, Rodrigues M, Calderbank R. Information-theoretic criteria for the design of compressive subspace classifiers. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2014 Jan 1;3067–71.
Nokleby, M., et al. “Information-theoretic criteria for the design of compressive subspace classifiers.” ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Jan. 2014, pp. 3067–71. Scopus, doi:10.1109/ICASSP.2014.6854164.
Nokleby M, Rodrigues M, Calderbank R. Information-theoretic criteria for the design of compressive subspace classifiers. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2014 Jan 1;3067–3071.
Published In
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
DOI
ISSN
1520-6149
Publication Date
January 1, 2014
Start / End Page
3067 / 3071