A PAC-Bayesian margin bound for linear classifiers: Why SVMS Work

Advances in Neural Information Processing Systems

Volumn , Issue , 2001, Pages

  Herbrich, Ralf ^a   Graepel, Thore ^a  

^a TECHNISCHE UNIVERSITÄT BERLIN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

SUPPORT VECTOR MACHINES;

BENCHMARK DATA; FEATURE VECTORS; GENERALISATION; HYPOTHESIS SPACE; INPUT DIMENSIONS; LINEAR CLASSIFIERS; NUMERICAL EXPERIMENTS; TRAINING EXAMPLE;

CLASSIFICATION (OF INFORMATION);

EID: 84894167296     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. N. Alon, S. Ben-David, N. Cesa-Bianchi, and D. Haussler. Scale sensitive dimensions, uniform convergence and learnability. Journal of the ACM, 44(4):615-631, 1997.
2. R. Herbrich. Learning Linear Classifiers - Theory and Algorithms. PhD thesis, Technische Universität Berlin, 2000. accepted for publication by MIT Press.
3. R. Herbrich, T. Graepel, and C. Campbell. Bayesian learning in reproducing kernel Hilbert spaces. Technical report, Technical University of Berlin, 1999. TR 99-11.
4. M. J. Kearns and R. Schapire. Efficient distribution-free learning of probabilistic concepts. Journal of Computer and System Sciences, 48(2):464-497, 1993.
5. D. A. McAllester. Some PAC Bayesian theorems. In Proceedings of the Eleventh Annual Conference on Computational Learning Theory, pages 230-234, Madison, Wisconsin, 1998.
6. N. Sauer. On the density of families of sets. Journal of Combinatorial Theory, Series A, 13:145-147, 1972.
7. R. E. Schapire, Y. Freund, P. Bartlett, and W. S. Lee. Boosting the margin: A new explanation for the effectiveness of voting methods. In Proceedings of the 14-th International Conference in Machine Learning, 1997.
8. J. Shawe-Taylor, P. L. Bartlett, R. C. Williamson, and M. Anthony. Structural risk minimization over data-dependent hierarchies. IEEE Transactions on Information Theory, 44(5):1926-1940, 1998.
9. J. Shawe-Taylor and R. C. Williamson. A PAC analysis of a Bayesian estimator. Technical report, Royal Holloway, University of London, 1997. NC2-TR-1997-013.
10. UCI. University of California Irvine: Machine Learning Repository, 1990.
11. L. G. Valiant. A theory of the learnable. Communications of the ACM, 27(11):1134-1142, 1984.
12. V. Vapnik. Estimation of Dependences Based on Empirical Data. Springer, 1982.
13. V. Vapnik. The Nature of Statistical Learning Theory. Springer, 1995.
14. V. Vapnik and A. Chervonenkis. On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Application, 16(2):264-281, 1971.