How to construct random functions
Journal of the ACM (JACM)
Probably almost Bayes decisions
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
A Pseudorandom Generator from any One-way Function
SIAM Journal on Computing
Exploiting generative models in discriminative classifiers
Proceedings of the 1998 conference on Advances in neural information processing systems II
When Can Two Unsupervised Learners Achieve PAC Separation?
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
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)
Discriminative learning can succeed where generative learning fails
Information Processing Letters
Information, Divergence and Risk for Binary Experiments
The Journal of Machine Learning Research
Universal prediction of selected bits
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
| Hi-index | 0.00 |
Generative algorithms for learning classifiers use training data to separately estimate a probability model for each class. New items are then 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 (given minimal cryptographic assumptions). This statement is formalized using a framework inspired by previous work of Goldberg [3].