Discriminative learning can succeed where generative learning fails
Venue
Information Processing Letters, vol. 103(4) (2007), pp. 131-135
Publication Year
2007
Authors
Philip M. Long, Rocco A. Servedio, Hans Ulrich Simon
BibTeX
Abstract
Generative algorithms for learning classifiers use training data to separately
estimate a probability model for each class. New items are classified by comparing
their probabilities under these models. In contrast, discriminative learning
algorithms try to find classifiers that perform well on all the training data.
We show that there is a learning problem that can be solved by a discriminative learning algorithm, but not by any generative learning algorithm. This statement is formalized using a framework inspired by previous work of Goldberg.
