New estimation and feature selection methods in mixture-of-experts models

作者：Khalili Abbas^*

来源：Canadian Journal of Statistics, 2010, 38(4): 519-539.

DOI：10.1002/cjs.10083

• Mixture-of experts
• regularization
• LASSO
• SCAD
• EM algorithms

We study estimation and feature selection problems in mixture of-experts models An l(2) penalized maximum likelihood estimator is proposed as an alternative to the ordinary maximum likelihood estimator The estimator is particularly advantageous when fitting a mixture-of experts model to data with many correlated features It is shown that the proposed estimator is root n consistent and simulations show its superior finite sample behaviour compared to that of the maximum likelihood estimator For feature selection two extra penalty functions are applied to the l(2)-penalized log likelihood function The proposed feature selection method is computationally much more efficient than the popular all-subset selection methods Theoretically it is shown that the method is consistent in feature select

• 出版日期2010-12