On efficient agnostic learning of linear combinations of basis functions

Proceedings of the 8th Annual Conference on Computational Learning Theory, COLT 1995

Volumn 1995-January, Issue , 1995, Pages 369-376

  Lee, Wee Sun ^a   Bartlett, Peter L ^a   Williamson, Robert C ^a  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

ABSOLUTE VALUES; AGNOSTIC LEARNING; BASIS FUNCTIONS; COMBINATORIAL PROPERTIES; LINEAR COMBINATIONS; LOSS FUNCTIONS; QUADRATIC LOSS FUNCTIONS; SAMPLE COMPLEXITY;

FUNCTIONS;

EID: 77952326343     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/225298.225343     Document Type: Conference Paper

References (20)

1. A. Aho, J. Hopcroft, and J. Ullman. The Design and Analysis of Computer Algorithms. Addison-Wesley, London, 1974.
2. N. Alon, S. Ben-David, N. Cesa-Bianchi, and D. Haussler. Scale-sensitive dimensions, uniform convergence and learnability. In Proc. 35th Annu. IEEE Sympos. Found. Comput. Sci., 1993.
3. D. Angluin and L. Valiant. Fast probabilistic algorithms for hamiltonian circuits and matching. J. Comput. Syst. Sci., 18:155-193, 1970.
4. M. Anthony and N. Biggs. Computational Learning Theory. Cambridge Tracts in Theoretical Computer Science (30). Cambridge University Press, 1992.
5. A. Barron. Universal approximation bounds for superposition of a sigmoidal function. IEEE Trans, on Information Theory, 39:930-945, 1993.
6. P. L. Bartlett, P. M. Long, and R. C. Williamson. Fatshattering and the learnability of real-valued functions. In Proc. 7th Annu. ACM Workshop on Comput. Learning Theory, pages 299-310. ACM Press, New York, NY, 1994.
7. A. Blumer, A. Ehrenfeucht, D. Haussler, and M. K. Warmuth. Learnability and the Vapnik-Chervonenkis dimension. J. ACM, 36(4):929-965, 1989.
8. L. Gurvits and P. Koiran. Approximation and learning of real-valued functions. In Proc. 2nd European Conf. on Comput. Learning Theory, 1995.
9. D. Haussler. Decision theoretic generalizations of the PAC model for neural net and other learning applications. Inform. Comput., 100(1):78-150, September 1992.
10. W Hoeffding. Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association, 58(301):13-30, March 1963.
11. K. Hoffgen and H. Simon. Robust trainability of single neurons. In Proc. 5th Annu. Workshop on Comput. Learning Theory, pages 428-439, New York, NY, 1992. ACM Press.
12. M. Jerrum. Simple translation-invariant concepts are hard to learn. Inform. Comput, 113(2):300-311, September 1994.
13. L. K. Jones. A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. The Annals of Statistics, 20:608-613, 1992.
14. M. J. Kearns and R. E. Schapire. Efficient distributionfree learning of probabilistic concepts. J. Comput. Syst. Sci., 48(3):464, 1994.
15. M. J. Kearns, R. E. Schapire, and L. M. Sellie. Toward efficient agnostic learning. Machine Learning, 17(2):115, 1994.
16. P. Koiran. Efficient learning of continuous neural networks. In Proc. 7th Annu. ACM Workshop on Comput. Learning Theory, pages 348-355. ACM Press, New York, NY, 1994.
17. W. S. Lee, P. L. Bartlett, and R. C. Williamson. Efficient agnostic learning of neural networks with bounded fan-in. Technical report, Department of Systems Engineering, Australian National University, 1994.
18. W. Maass. Agnostic PAC-learning of functions on analog neural networks. Technical report, Institute for Theoretical Computer Science, Technische Universitaet Graz, Graz, Austria, 1993.
19. R. E. Schapire. The strength of weak learnability. Machine Learning, 5(2):197-227, 1990.
20. L. G. Valiant. A theory of the learnable. Commun. ACM, 27(11):1134-1142, November 1984.