Reboredo, H;
Renna, F;
Calderbank, R;
Rodrigues, MRD;
(2016)
Bounds on the Number of Measurements for Reliable Compressive Classification.
IEEE Transactions on Signal Processing
, 64
(22)
pp. 5778-5793.
10.1109/TSP.2016.2599496.
Preview |
Text
Rodrigues_07542135.pdf Download (1MB) | Preview |
Abstract
This paper studies the classification of high-dimensional Gaussian signals from low-dimensional noisy, linear measurements. In particular, it provides upper bounds (sufficient conditions) on the number of measurements required to drive the probability of misclassification to zero in the low-noise regime, both for random measurements and designed ones. Such bounds reveal two important operational regimes that are a function of the characteristics of the source: 1) when the number of classes is less than or equal to the dimension of the space spanned by signals in each class, reliable classification is possible in the low-noise regime by using a one-vs-all measurement design; 2) when the dimension of the spaces spanned by signals in each class is lower than the number of classes, reliable classification is guaranteed in the low-noise regime by using a simple random measurement design. Simulation results both with synthetic and real data show that our analysis is sharp, in the sense that it is able to gauge the number of measurements required to drive the misclassification probability to zero in the low-noise regime.
| Type: | Article |
|---|---|
| Title: | Bounds on the Number of Measurements for Reliable Compressive Classification |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/TSP.2016.2599496 |
| Publisher version: | http://doi.org/10.1109/TSP.2016.2599496 |
| Language: | English |
| Additional information: | This work is licensed under a Creative Commons Attribution 3.0 License. For more information, see http://creativecommons.org/licenses/by/3.0/ |
| Keywords: | Science & Technology, Technology, Engineering, Electrical & Electronic, Engineering, Compressed sensing, compressive classification, classification, dimensionality reduction, Gaussian mixture models, measurement design, phase transitions, random measurements, TASK-SPECIFIC INFORMATION, LINEAR-SUBSPACES, FACE RECOGNITION, FEATURE-EXTRACTION, GAUSSIAN MIXTURE, RECONSTRUCTION, SIGNALS, ALGORITHM, MANIFOLDS, RECOVERY |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/1529768 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
