Discriminative learning can succeed where generative learning fails

Information Processing Letters

Volumn 103, Issue 4, 2007, Pages 131-135

  Long, Philip M ^a   Servedio, Rocco A ^b   Simon, Hans Ulrich ^c  

^a GOOGLE INC   (United States)

^b Och Spine at New York Presbyterian Hospitals   (United States)

^c RUHR UNIVERSITY BOCHUM   (Germany)

Author keywords

Algorithms; Computational learning theory; Discriminative learning; Generative learning; Machine learning

Indexed keywords

CLASSIFICATION (OF INFORMATION); INFORMATION USE; LEARNING SYSTEMS; PROBLEM SOLVING;

COMPUTATIONAL LEARNING THEORY; DISCRIMINATIVE LEARNING; GENERATIVE LEARNING; LEARNING PROBLEMS;

LEARNING ALGORITHMS;

EID: 34248560655     PISSN: 00200190     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ipl.2007.03.004     Document Type: Article

References (12)

1. Anoulova S., Fischer P., Pölt S., and Simon H.U. Probably almost Bayes decisions. Information and Computation 129 1 (1996) 63-71
2. Duda R.O., Hart P.E., and Stork D.G. Pattern Classification. second ed. (2000), Wiley
3. Ehrenfeucht A., Haussler D., Kearns M., and Valiant L.G. A general lower bound on the number of examples needed for learning. Information and Computation 82 3 (1989) 247-251
4. P. Goldberg, When can two unsupervised learners achieve PAC separation?, in: Proceedings of the 14th Annual COLT, 2001, pp. 303-319
5. Goldberg P. Some discriminant-based PAC algorithms. Journal of Machine Learning Research 7 (2006) 283-306
6. Jaakkola T., and Haussler D. Exploiting generative models in discriminative classifiers. Advances in NIPS vol. 11 (1998), Morgan Kaufmann 487-493
7. Jebara T. Machine Learning: Discriminative and Generative (2003), Kluwer
8. P. M. Long, R. A. Servedio, Discriminative learning can succeed where generative learning fails, in: Proc. 19th Conference on Computational Learning Theory, 2006, pp. 319-334
9. A. Y. Ng, M. I. Jordan, On discriminative vs. generative classifiers: A comparison of logistic regression and naive Bayes, NIPS, 2001
10. R. Raina, Y. Shen, A. Y. Ng, A. McCallum, Classification with hybrid generative/discriminative models, NIPS, 2004
11. Valiant L.G. A theory of the learnable. Proc. 16th Annual ACM Symposium on Theory of Computing (STOC) (1984), ACM Press 436-445
12. Vapnik V. Estimations of Dependences Based on Statistical Data (1982), Springer