A general lower bound on the number of examples needed for learning
Information and Computation
Probably almost Bayes decisions
Information and Computation
Exploiting generative models in discriminative classifiers
Proceedings of the 1998 conference on Advances in neural information processing systems II
STOC '84 Proceedings of the sixteenth annual ACM symposium on Theory of computing
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Machine Learning: Discriminative and Generative (Kluwer International Series in Engineering and Computer Science)
Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)
Some Discriminant-Based PAC Algorithms
The Journal of Machine Learning Research
Discriminative learning can succeed where generative learning fails
COLT'06 Proceedings of the 19th annual conference on Learning Theory
| Hi-index | 0.89 |
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 [P. Goldberg, When can two unsupervised learners achieve PAC separation?, in: Proceedings of the 14th Annual COLT, 2001, pp. 303-319].