Classification Based on a Permanental Process with Cyclic Approximation

• Activity Number: 249
• Type: Contributed
• Date/Time: Monday, July 30, 2012 : 2:00 PM to 3:50 PM
• Sponsor: IMS
• Author(s): Jie Yang*+ and Klaus Miescke and Peter McCullagh
• Companies: University of Illinois at Chicago and University of Illinois at Chicago and The University of Chicago
• Keywords: Cyclic approximation ; DNA microarray analysis ; Virus classification ; High-dimensional data ; Supervised classification ; Weighted permanental ratio

Abstract

In this talk 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 model is effective even if the feature region occupied by one class is a patchwork interlaced with regions occupied by other classes. The classification criterion involves a permanental ratio for which an approximation using a polynomial-time cyclic expansion is proposed. Applications to DNA microarray analysis and virus classification indicate 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.