File(s) under permanent embargo
MassBayes: a new generative classifier with multi-dimensional likelihood estimation
conference contribution
posted on 2013-01-01, 00:00 authored by Sunil AryalSunil Aryal, Kai Ming TingExisting generative classifiers (e.g., BayesNet and AnDE) make independence assumptions and estimate one-dimensional likelihood. This paper presents a new generative classifier called MassBayes that estimates multi-dimensional likelihood without making any explicit assumptions. It aggregates the multi-dimensional likelihoods estimated from random subsets of the training data using varying size random feature subsets. Our empirical evaluations show that MassBayes yields better classification accuracy than the existing generative classifiers in large data sets. As it works with fixed-size subsets of training data, it has constant training time complexity and constant space complexity, and it can easily scale up to very large data sets.