Classification based on a permanental process with cyclic approximation
Abstract
We introduce a doubly stochastic marked point process model for supervised classification problems. Regardless of the number of classes or the dimension of the feature space, the model requires only 2--3 parameters for the covariance function. The classification criterion involves a permanental ratio for which an approximation using a polynomial-time cyclic expansion is proposed. The approximation is effective even if the feature region occupied by one class is a patchwork interlaced with regions occupied by other classes. An application to DNA microarray analysis indicates that the cyclic approximation is effective even for high-dimensional data. It can employ feature variables in an efficient way to reduce the prediction error significantly. This is critical when the true classification relies on non-reducible high-dimensional features.
- Publication:
-
arXiv e-prints
- Pub Date:
- August 2011
- DOI:
- 10.48550/arXiv.1108.4920
- arXiv:
- arXiv:1108.4920
- Bibcode:
- 2011arXiv1108.4920Y
- Keywords:
-
- Statistics - Methodology;
- Statistics - Applications
- E-Print:
- 12 pages, 3 figures