Abstract
The standard PAC model focuses on learning a class of functions from labeled examples, where the two critical resources are the number of examples needed and running time. In many natural learning problems, however, unlabeled data can be obtained much more cheaply than labeled data. This has motivated the notion of semi-supervised learning, in which algorithms attempt to use this cheap unlabeled data in a way that (hopefully) reduces the number of labeled examples needed for learning [4]. For instance, semi-supervised and transductive SVM [2,5] and co-training [3] are two examples of semi-supervised learning algorithms. In [1], a semi-supervised PAC model is introduced that provides a common framework for the kinds of assumptions these algorithms make; however, most of the results in [1] deal with sample complexity rather than computational efficiency, or are only computationally efficient under strong assumptions on the underlying distribution. This note poses several questions related to developing computationally efficient algorithms in this semi-supervised PAC model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balcan, M.-F., Blum, A.: A PAC-style model for learning from labeled and unlabeled data. In: Proc. 18th Annual Conference on Learning Theory (2005)
Bennett, K. P., Demiriz, A.: Semi-supervised support vector machines. In: NIPS, pp. 368–374 (1998)
Blum, A., Mitchell, T.M.: Combining labeled and unlabeled data with co-training. In: Proc. 11th Annual Conference on Learning Theory, pp. 92–100 (1998)
Chapelle, O., Schölkopf, B., Zien, A. (eds.): Semi-Supervised Learning. MIT Press, Cambridge (2006)
Joachims, T.: Transductive inference for text classification using support vector machines. In: Proc. ICML, pp. 200–209 (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Blum, A., Balcan, MF. (2007). Open Problems in Efficient Semi-supervised PAC Learning. In: Bshouty, N.H., Gentile, C. (eds) Learning Theory. COLT 2007. Lecture Notes in Computer Science(), vol 4539. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72927-3_45
Download citation
DOI: https://doi.org/10.1007/978-3-540-72927-3_45
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72925-9
Online ISBN: 978-3-540-72927-3
eBook Packages: Computer ScienceComputer Science (R0)