Learning kernel-based halfspaces with the zero-one loss

COLT 2010 - The 23rd Conference on Learning Theory

Volumn , Issue , 2010, Pages 441-450

  Shalev Shwartz, Shai ^a   Shamir, Ohad ^a   Sridharan, Karthik ^b  

^a HEBREW UNIVERSITY OF JERUSALEM   (Israel)

^b TOYOTA TECHNOLOGICAL INSTITUTE   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CRYPTOGRAPHIC ASSUMPTIONS; FINITE TIME; HALF SPACES; HARDNESS RESULT; LIPSCHITZ CONSTANT; LOGISTIC REGRESSIONS; LOSS FUNCTIONS; TIME POLYNOMIALS;

ALGORITHMS;

EID: 84898062142     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (27)

1. C. Thomas-Agnan A. Berlinet. Reproducing Kernel Hilbert Spaces in Probability and Statistics. Springer, 2003.
2. P. L. Bartlett. For valid generalization, the size of the weights is more important than the size of the network. In Advances in Neural Information Processing Systems 9, 1997.
3. P. L. Bartlett and S. Mendelson. Rademacher and Gaussian complexities: Risk bounds and structural results. Journal of Machine Learning Research, 3:463-482, 2002.
4. P. L. Bartlett, M. I. Jordan, and J. D. McAuliffe. Convexity, classification, and risk bounds. Journal of the American Statistical Association, 101:138-156, 2006.
5. S. Ben-David. Alternative measures of computational complexity. In TAMC, 2006.
6. S. Ben-David and H. Simon. Efficient learning of linear perceptrons. In NIPS, 2000.
7. E. Blais, R. O'Donnell, and K Wimmer. Polynomial regression under arbitrary product distributions. In COLT, 2008.
8. L. Bottou and O. Bousquet. The tradeoffs of large scale learning. In NIPS, pages 161-168, 2008.
9. O. Bousquet. Concentration Inequalities and Empirical Processes Theory Applied to the Analysis of Learning Algorithms. PhD thesis, Ecole Polytechnique, 2002.
10. N. Cristianini and J. Shawe-Taylor. Kernel Methods for Pattern Analysis. Cambridge University Press, 2004.
11. V. Feldman, P. Gopalan, S. Khot, and A.K. Ponnuswami. New results for learning noisy parities and halfspaces. In In Proceedings of the 47th Annual IEEE Symposium on Foundations of Computer Science, 2006.
12. V. Guruswami and P. Raghavendra. Hardness of learning halfspaces with noise. In Proceedings of the 47th Foundations of Computer Science (FOCS), 2006.
13. S.M. Kakade, K. Sridharan, and A. Tewari. On the complexity of linear prediction: Risk bounds, margin bounds, and regularization. In NIPS, 2008.
14. A. Kalai, A.R. Klivans, Y. Mansour, and R. Servedio. Agnostically learning halfspaces. In Proceedings of the 46th Foundations of Computer Science (FOCS), 2005.
15. M. J. Kearns, R. E. Schapire, and L. M. Sellie. Toward efficient agnostic learning. In COLT, pages 341-352, July 1992. To appear, Machine Learning.
16. Adam R. Klivans and Alexander A. Sherstov. Cryptographic hardness for learning intersections of halfspaces. In FOCS, 2006.
17. D. A. McAllester. Simplified PAC-Bayesian margin bounds. In COLT, pages 203-215, 2003.
18. R.E. Schapire. The strength of weak learnability. Machine Learning, 5(2):197-227, 1990.
19. B. Schölkopf and A. J. Smola. Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, 2002.
20. S. Shalev-Shwartz and N. Srebro. SVM optimization: Inverse dependence on training set size. In International Conference on Machine Learning, pages 928-935, 2008.
21. S. Shalev-Shwartz, O. Shamir, and K. Sridharan. Agnostically learning halfspaces with margin errors. Technical report, Toyota Technological Institute, 2009.
22. S. Shalev-Shwartz, O. Shamir, and K. Sridharan. Learning kernel-based halfspaces with the zero-one loss, 2010. Technical Report, available at arXiv:1005.3681.
23. I. Steinwart and C. Scovel. Fast rates for support vector machines using gaussian kernels. Annals of Statistics, 35:575, 2007.
24. A. Tsybakov. Optimal aggregation of classifiers in statistical learning. Annals of Statistics, 32: 135-166, 2004.
25. V. N. Vapnik. Statistical Learning Theory. Wiley, 1998.
26. G. Wahba. Spline Models for Observational Data. SIAM, 1990.
27. T. Zhang. Statistical behavior and consistency of classification methods based on convex risk minimization. The Annals of Statistics, 32:56-85, 2004.