Summary: The Multilevel Classification Problem and a
Monotonicity Hint
Malik Magdon-Ismail1
, Hung-Ching (Justin) Chen1
, and
Yaser S. Abu-Mostafa2
1
Dept. of Computer Science, RPI, Lally 207,
110 8th Street, Troy, NY, USA 12180
{magdon, chenh3}@rpi.edu
2
Learning Systems Group,136-93,Caltech, Pasadena, CA, USA, 91125
yaser@cs.caltech.edu
Abstract. We introduce and formalize the multilevel classification
problem, in which each category can be subdivided into different lev-
els. We analyze the framework in a Bayesian setting using Normal class
conditional densities. Within this framework, a natural monotonicity hint
converts the problem into a nonlinear programming task, with non-linear
constraints. We present Monte Carlo and gradient based techniques for
addressing this task, and show the results of simulations. Incorporation

Source: Abu-Mostafa, Yaser S. - Department of Mechanical Engineering & Computer Science Department, California Institute of Technology

Collections: Computer Technologies and Information Sciences