Abstract
Can we learn from unlabeled examples? We consider here the un-supervised learning scenario in which the examples provided are not labeled (and are not necessarily all positive or all negative). The only information about their membership is indirectly disclosed to the student through the sampling distribution.
We view this problem as a restricted instance of the fundamental issue of inferring information about a probability distribution from the random samples it generates. We propose a framework, density-level-learning, for acquiring some partial information about a distribution and develop a model of un-supervised concept learning based on this framework.
We investigate the basic features of these types of learning and provide lower and upper bounds on the sample complexity of these tasks. Our main result is that the learnability of a class in this setting is equivalent to the finiteness of its VC-dimension. One direction of the proof involves a reduction of the density-level-learnability to PAC learnability, while the sufficiency condition is proved through the introduction of a generic learning algorithm.
This research was supported by the David and Ruth Moskowitz Academic Lectureship.
Preview
Unable to display preview. Download preview PDF.
References
S. Ben-David and M. Lindenbaum, 1993, “Localization vs. Identification of Semi-Algebraic Sets”, Proc. COLT 93, pp. 327–336.
Blumer, A., A. Ehrenfeucht, D. Haussler and M.K. Warmuth, 1989, “Learnability and The Vapnik-Chervonenkis Dimension”, JACM, 36(4), pp. 929–965.
Canetti, R., G. Even and O. Goldreich, 1993, “Lower Bounds for sampling Algorithms for Estimating the Average”, Computer Science Technical Report No. 789, Technion-Israel Institute of Technology.
Duda, R.O., and P.E. Hart, 1973, “Pattern Classification and Scene Analysis”, Wiley.
Dudley, R.M., 1984, “A course on empirical processes”, Lecture Notes in Mathematics, 1097, pp. 2–142.
Illingworth, J., and J. Kittler, 1988 “A Survey of Hough Transform”, Computer Vision, Graphics, and Image Processing, 44, pp. 87–116.
Khovanskii, A.G. 1991, “Fewnomials”, Translations of Mathematical Monographs, 88.
Kearns, M., Y. Mansour, D. Ron, R. Rubinfeld, R.E. Schapire, and L. Sellie, 94, “On the Learnability of Discrete Distributions”, Proc. of 26th ACM STOC 94, pp. 273–282.
Kim, W.M., 991, “Learning by Smoothing: a Morphological approach”, Proc. of COLT 91, pp. 43–57.
Natarajan, B.K., 1991, “Probably Approximate Learning of Sets and Functions”, SIAM J. Comput. 20(1), pp. 328–351.
Papoulis, A., 1984, “Probability, Random Variables, and Stochastic Processes”, 1984, McGraw-Hill.
Vapnik, V.N. and A.Y. Chervonenkis, 1971, “On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities”, Theory of Probability and its applications, 16(2), pp. 264–280.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ben-David, S., Lindenbaum, M. (1995). Learning distributions by their density levels — A paradigm for learning without a teacher. In: Vitányi, P. (eds) Computational Learning Theory. EuroCOLT 1995. Lecture Notes in Computer Science, vol 904. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59119-2_168
Download citation
DOI: https://doi.org/10.1007/3-540-59119-2_168
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59119-1
Online ISBN: 978-3-540-49195-8
eBook Packages: Springer Book Archive