Budgeted Learning of Naive-Bayes Classifiers
Full Text:
Budget-NB.ps 
There is almost always a cost associated with acquiring training data. We consider the situation where the learner, with a fixed budget, may `purchase' data during training. In particular, we examine the case where observing the value of a feature of a training example has an associated cost, and the total cost of all feature values acquired during training must remain less than this fixed budget. This paper compares methods for sequentially choosing which feature value topurchase next, given the budget and user's current knowledge of Naive Bayes model parameters. Whereas active learning hastraditionally focused on myopic (greedy) approaches and uniform/round-robin policies for query selection, this paper shows that such methods are often suboptimal and presents a tractable method for incorporating knowledge of the budget in the information acquisition process.
Citation
D. Lizotte,
O. Madani,
R. Greiner.
"Budgeted Learning of Naive-Bayes Classifiers".
Conference on Uncertainty in Artificial Intelligence (UAI), Acapulco, Mexico, August 2003.
| Keywords: |
budgeted learning, active learning, machine learning |
| Category: |
In Conference |
BibTeX
@incollection{Lizotte+al:UAI03,
author = {Dan Lizotte and Omid Madani and Russ Greiner},
title = {Budgeted Learning of Naive-Bayes Classifiers},
booktitle = {Conference on Uncertainty in Artificial Intelligence (UAI)},
year = 2003,
}Last Updated: April 24, 2007
Submitted by Russ Greiner 
