On the Value of Partial Information for Learning from Examples

Journal of Complexity

Volumn 13, Issue 4, 1997, Pages 509-544

  Ratsaby, Joel ^a   Maiorov, Vitaly ^a  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0009142588     PISSN: 0885064X     EISSN: None     Source Type: Journal    
DOI: 10.1006/jcom.1997.0459     Document Type: Article

References (40)

1. Abu-Mostafa Y. S. Learning from hints in neural networks. J. Complexity. 6:1990;192-198.
2. Abu-Mostafa Y. S. Hints and the VC dimension. Neural Comput. 5:1993;278-288.
3. Abu-Mostafa Y. S. Machines that learn from hints. Sci. Am. 272:1995.
4. N. Alon, S. Ben-David, N. Cesa-Bianchi, D. Haussler, 1993, Scale-sensitive dimensions, uniform convergence, and learnability, Proceedings, 34th Annual Symposium on Foundations of Computer Science, 292, 301, IEEE Comput. Soc. Press, Los Alamitos, CA.
5. P. L. Bartlett, P. M. Long, R. C. Williamson, 1994, Fat-shattering and the learnability of real-valued functions, Proceedings of the 7th Annual Conference on Computational Learning Theory, 299, ACM, New York, NY.
6. α. 2:1967;295-317.
7. Blumer A., Ehrenfeucht A., Haussler D., Warmuth M. Learnability and the Vapnik-Chervonenkis dimension. J. Assoc. Comput. Mach. 36:1989;929-965.
8. Buescher K. L., Kumar P. R. Learning by canonical smooth estimation, Part I: Simultaneous estimation. IEEE Trans. Automat. Control. 41:1996;545-545.
9. Cohn D. Neural network exploitation using optimal experiment design. Neural Networks. 9:1996;1071-1083.
10. Cohn D., Atlas L., Ladner R. Improving generalization with active learning. Mach. Learning. 15:1994;201-221.
11. Devore R. A. Degree of nonlinear approximation. Approximation Theory VI. 1989;Academic Press, San Diego. p. 175-201.
12. Devroye L. A course in density estimation. Progress in Probability and Statistics. 1987;Birkhauser, Boston.
13. Devroye L., Gyorfi L., Lugosi G. A Probabilistic Theory of Pattern Recognition. 1996;Springer-Verlag, New York/Berlin.
14. Duda R. O., Hart P. E. Pattern Classification and Scene Analysis. 1973;Wiley, New York.
15. Fukunaga K. Introduction to Statistical Pattern Recognition. 1990;Academic Press, Boston.
16. Hanson S., Petsche T., Kearns M., Rivest R. Computational Learning Theory and Natural Learning Systems. 1996;MIT Press, Cambridge.
17. Haussler D. Decision theoretic generalizations of the PAC model for neural net and other learning applications. Inform. Comput. 100:1992;78-150.
18. Hoeffding W. Probability inequalities for sums of bounded random variables. J. Amer. Statist. Assoc. 58:1963;13-30.
19. Kearns M. J., Vazirani U. An Introduction to Computational Learning Theory. 1997;MIT Press.
20. Linhart H., Zucchini W. Model Selection. Wiley Series in Probability and Mathematical Statistics. 1986;Wiley, New York.
21. Maiorov V. E. On best approximation by ridge functions. J. Approx. Theory. 1996.
22. Maiorov V. E., Meir R., Ratsaby J. On the approximation of functional classes equipped with a uniform measure using ridge functions. J. Approx. Theory. 1996.
23. ∞r. J. Approx. Theory. 84:1996.
24. Maiorov V., Ratsaby J. On the degree of approximation using manifolds of finite pseudo-dimension. J. Constr. Approx. 1997.
25. Petrov V. V. Sums of Independent Random Variables. 1975;Springer-Verlag, Berlin.
26. Pinkus A. n. 1985;Springer-Verlag, New York.
27. Pollard D. Convergence of Stochastic Processes. Springer Series in Statistics. 1984;Springer-Verlag, Berlin/New York.
28. Pollard D. Empirical Processes: Theory and Applications. NSF-CAMS Regional Conference Series in Probability and Statistics. 2:1989;Inst. Math. Stat. Am. Stat. Assoc. Hayward.
29. J. Ratsaby, 1994, The Complexity of Learning from a Mixture of Labeled and Unlabeled Examples, University of Pennsylvania.
30. J. Ratsaby, R. Meir, V. Maiorov, 1996, Towards robust model selection using estimation and approximation error bounds, Proc. 9th Annual Conference on Computational Learning Theory, 57, 57, ACM, New York, NY.
31. J. Ratsaby, S. S. Venkatesh, 1995, Learning from a mixture of labeled and unlabeled examples, Proc. 33rd Allerton Conferene on Communication Control and Computing, 1002, 1009.
32. J. Ratsaby, S. S. Venkatesh, 1995, Learning from a mixture of labeled and unlabeled examples with parametric side information, Proc. 8th Annual Conference on Computational Learning Theory, 412, 412, Morgan Kaufmann, San Mateo, CA.
33. Ripley B. D. Pattern Recognition and Neural Networks. 1996;Cambridge University Press, Cambridge.
34. Tikhomirov V. M. Some Problems in Approximation Theory. 1976;Moscow State University.
35. Traub J. F., Wasilkowski G. W., Wozniakowski H. Information-Based Complexity. 1988;Academic Press, San Diego.
36. Valiant L. G. A theory of the learnable. Comm. ACM. 27:1984;1134-1142.
37. Vapnik V. N., Chervonenkis A. Ya. On the uniform convergence of relative frequencies of events to their probabilities. Theoret. Probl. Appl. 16:1971;264-280.
38. Vapnik V. N., Chervonenkis A. Ya. Necessary and sufficient conditions for the uniform convergence of means to their expectations. Theoret. Probl. Appl. 26:1981;532-553.
39. Vapnik V. N. Estimation of Dependences Based on Empirical Data. 1982;Springer-Verlag, Berlin.
40. Warren H. E. Lower bounds for approximation by non-linear manifolds. Trans. Amer. Math. Soc. 133:1968;167-178.