Math @ Duke

Publications [#303199] of Robert Calderbank
Papers Published
 Reboredo, H; Renna, F; Calderbank, R; Rodrigues, MRD, Compressive Classification
(February, 2013) [1302.4660v1]
(last updated on 2018/10/19)
Abstract: This paper derives fundamental limits associated with compressive
classification of Gaussian mixture source models. In particular, we offer an
asymptotic characterization of the behavior of the (upper bound to the)
misclassification probability associated with the optimal MaximumAPosteriori
(MAP) classifier that depends on quantities that are dual to the concepts of
diversity gain and coding gain in multiantenna communications. The diversity,
which is shown to determine the rate at which the probability of
misclassification decays in the low noise regime, is shown to depend on the
geometry of the source, the geometry of the measurement system and their
interplay. The measurement gain, which represents the counterpart of the coding
gain, is also shown to depend on geometrical quantities. It is argued that the
diversity order and the measurement gain also offer an optimization criterion
to perform dictionary learning for compressive classification applications.


dept@math.duke.edu
ph: 919.660.2800
fax: 919.660.2821
 
Mathematics Department
Duke University, Box 90320
Durham, NC 277080320

