Optimal Mistake Bound Learning Is Hard

Information and Computation

Volumn 144, Issue 1, 1998, Pages 66-82

  Frances, Moti ^a   Litman, Ami ^b  

^a IBM   (Israel)

^b TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0348229334     PISSN: 08905401     EISSN: None     Source Type: Journal    
DOI: 10.1006/inco.1998.2709     Document Type: Article

References (7)

1. Blumer, A., Ehrenfeucht, A., Haussler, D., and Warmuth, M. K. (1989), Learnability and the Vapnik-Chervonenkis dimension, J. Assoc. Comput. Mach. 36(4), 929-965.
2. Hyafil, L., and Rivest, R. L. (1976), Constructing optimal binary decision trees is NP-complete, Inform. Proc. Lett. 5, 15-17.
3. Littlestone, N. (1988), Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm, Mach. Learning 2, 285-318.
4. Papadimitriou, C. H., and Yannakakis, M. (1993), On limited nondeterminism and the complexity of the V-C dimension, Proceedings of the Eight Annual Structure in Complexity Theory Conference, pp. 12-18.
5. Shinohara, A. (1994), Complexity of computing generalized VC-dimensions, Machine Learning: ECML-94 (F. Bergadano and L. DeRaedt, Eds.), Lecture Notes in Computer Science, Vol. 784, pp. 415-418, Springer-Verlag, Berlin/New York.
6. Valiant, L. G. (1984), A theory of the learnable, Comm. Assoc. Comput. Mach. 27(11), 1134-1142.
7. Vapnik, V. N., and Chervonenkis, A. Y. (1971), On the uniform convergence of relative frequencies of events to their probabilities, Theoret. Probab. Appl. 16, 264-280.