Classification based on a permanental process with cyclic approximation

TL;DR

This paper presents a novel probabilistic classification model using a permanental process with a cyclic approximation, effective for high-dimensional data and requiring minimal parameters, demonstrated on DNA microarray analysis.

Contribution

The paper introduces a new doubly stochastic point process model for classification that uses a polynomial-time cyclic approximation of the permanental ratio, suitable for high-dimensional and complex feature spaces.

Findings

Effective in high-dimensional DNA microarray data

Reduces prediction error significantly

Works with minimal parameters regardless of class or feature space size

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.