Math @ Duke

Publications [#235770] of Robert Calderbank
Papers Published
 Nokleby, M; Calderbank, R; Rodrigues, MRD, Informationtheoretic limits on the classification of Gaussian mixtures: Classification on the Grassmann manifold,
2013 IEEE Information Theory Workshop, ITW 2013
(December, 2013) [doi]
(last updated on 2018/10/21)
Abstract: Motivated by applications in highdimensional signal processing, we derive fundamental limits on the performance of compressive linear classifiers. By analogy with Shannon theory, we define the classification capacity, which quantifies the maximum number of classes that can be discriminated with low probability of error, and the diversitydiscrimination tradeoff, which quantifies the tradeoff between the number of classes and the probability of classification error. For classification of Gaussian mixture models, we identify a duality between classification and communications over noncoherent multipleantenna channels. This duality allows us to characterize the classification capacity and diversitydiscrimination tradeoff using existing results from multipleantenna communication. We also identify the easiest possible classification problems, which correspond to lowdimensional subspaces drawn from an appropriate Grassmann manifold. © 2013 IEEE.


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

