Math @ Duke

Publications [#326895] of Robert Calderbank
Papers Published
 Sokolić, J; Renna, F; Calderbank, R; Rodrigues, MRD, Mismatch in the classification of linear subspaces: Upper bound to the probability of error,
IEEE International Symposium on Information Theory  Proceedings, vol. 2015June
(September, 2015),
pp. 22012205, ISBN 9781467377041 [doi]
(last updated on 2018/07/22)
Abstract: © 2015 IEEE. This paper studies the performance associated with the classification of linear subspaces corrupted by noise with a mismatched classifier. In particular, we consider a problem where the classifier observes a noisy signal, the signal distribution conditioned on the signal class is zeromean Gaussian with lowrank covariance matrix, and the classifier knows only the mismatched parameters in lieu of the true parameters. We derive an upper bound to the misclassification probability of the mismatched classifier and characterize its behaviour. Specifically, our characterization leads to sharp sufficient conditions that describe the absence of an error floor in the lownoise regime, and that can be expressed in terms of the principal angles and the overlap between the true and the mismatched signal subspaces.


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

