Some discriminant-based PAC algorithms
UNSPECIFIED (2006) Some discriminant-based PAC algorithms. In: 14th Annual Conference on Computational Learning Theory (COLT 2001)/5th European Conference on Computational Learning Theory (EuroCOLT 2001), AMSTERDAM, NETHERLANDS, JUL 16-19, 2001. Published in: JOURNAL OF MACHINE LEARNING RESEARCH, 7 pp. 283-306.Full text not available from this repository.
A classical approach in multi-class pattern classification is the following. Estimate the probability distributions that generated the observations for each label class, and then label new instances by applying the Bayes classifier to the estimated distributions. That approach provides more useful information than just a class label; it also provides estimates of the conditional distribution of class labels, in situations where there is class overlap.
We would like to know whether it is harder to build accurate classifiers via this approach, than by techniques that may process all data with distinct labels together. In this paper we make that question precise by considering it in the context of PAC learnability. We propose two restrictions on the PAC learning framework that are intended to correspond with the above approach, and consider their relationship with standard PAC learning. Our main restriction of interest leads to some interesting algorithms that show that the restriction is not stronger (more restrictive) than various other well-known restrictions on PAC learning. An alternative slightly milder restriction turns out to be almost equivalent to unrestricted PAC learning.
|Item Type:||Conference Item (UNSPECIFIED)|
|Subjects:||Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
T Technology > TL Motor vehicles. Aeronautics. Astronautics
|Journal or Publication Title:||JOURNAL OF MACHINE LEARNING RESEARCH|
|Official Date:||February 2006|
|Number of Pages:||24|
|Page Range:||pp. 283-306|
|Title of Event:||14th Annual Conference on Computational Learning Theory (COLT 2001)/5th European Conference on Computational Learning Theory (EuroCOLT 2001)|
|Location of Event:||AMSTERDAM, NETHERLANDS|
|Date(s) of Event:||JUL 16-19, 2001|
Actions (login required)