NeuroCOLT

Neural Networks and Computational Learning Theory

 

About NeuroCOLT

Papers Archive

1994 1995
1996 1997
1998 1999
2000 2001

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-97-004

Comparing Predictive Inference Methods for Discrete Domains

Petri Kontkanen, Petri Myllymäki, Tom Silander, Henry Tirri
University of Helsinki
Finland

Peter Grunwald
CWI, Amsterdam
The Netherlands

Abstract
Predictive inference is seen here as the process of determining the predictive distribution of a discrete variable, given a data set of training examples and the values for the other problem domain variables. We consider three approaches for computing this predictive distribution, and assume that the joint probability distribution for the variables belongs to a set of distributions determined by a set of parametric models. In the simplest case, the predictive distribution is computed by using the model with the maximum a posteriori (MAP) posterior probability. In the evidence approach, the predictive distribution is obtained by averaging over all the individual models in the model family. In the third case, we define the predictive distribution by using Rissanen's new definition of stochastic complexity. Our experiments performed with the family of Naive Bayes models suggest that when using all the data available, the stochastic complexity approach produces the most accurate predictions in the log-score sense. However, when the amount of available training data is decreased, the evidence approach clearly outperforms the two other approaches. The MAP predictive distribution is clearly inferior in the log-score sense to the two more sophisticated approaches, but for the 0/1-score the MAP approach may still in some cases produce the best results.

Download Compressed Postscript
Title Page