Minimizing the misclassification error rate using a surrogate convex loss

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 2, Issue , 2012, Pages 1863-1870

  Ben David, Shai ^a   Loker, David ^a   Srebro, Nathan ^b   Sridharan, Karthik ^c  

^a UNIVERSITY OF WATERLOO   (Canada)

^b TOYOTA TECHNOLOGICAL INSTITUTE AT CHICAGO   (United States)

^c UNIVERSITY OF PENNSYLVANIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AGNOSTIC SETTING; BINARY CLASSIFICATION; ERROR RATE; LINEAR PREDICTORS; LOSS FUNCTIONS; MISCLASSIFICATION ERROR;

ARTIFICIAL INTELLIGENCE; SOFTWARE ENGINEERING;

LEARNING SYSTEMS;

EID: 84867129520     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Bartlett, P.L., Jordan, M.I., and McAuliffe, J.D. Convexity, classification, and risk bounds. Journal of the American Statistical Association, 101(473):138-156, 2006.
2. Ben-david, Shai and Simon, Hans Ulrich. Efficient learning of linear perceptrons. In Advances in Neural Information Processing Systems 13, pp. 189-195. MIT Press, 2000.
3. Christmann, Andreas and Steinwart, Ingo. On robustness properties of convex risk minimization methods for pattern recognition. J. Mach. Learn. Res., 5:1007-1034, December 2004. ISSN 1532-4435.
4. Kalai, Adam Tauman, Klivans, Adam R., Mansour, Yishay, and Servedio, Rocco A. Agnostically learning halfspaces. SIAM J. Comput, 37:1777-1805, March 2008. ISSN 0097-5397.
5. Kalai, A.T. and Sastry, R. The isotron algorithm: High-dimensional isotonic regression. In Proceedings of the 22th Annual Conference on Learning Theory. Citeseer, 2009.
6. Kearns, Michael, Schapire, Robert E., Sellie, Linda M., and Hellerstein, Lisa. Toward efficient agnostic learning. In Machine Learning, pp. 341-352. ACM Press, 1994.
7. Long, Phil and Servedio, Rocco A. Learning large-margin halfspaces with more malicious noise. In Advances in Neural Information Processing Systems 24, pp. 91-99. 2011.
8. Long, Philip M. and Servedio, Rocco A. Random classification noise defeats all convex potential boosters. In Proceedings of the 25th international conference on Machine learning, ICML '08, pp. 608-615, New York, NY, USA, 2008. ACM. ISBN 978-1-60558-205-4.
9. Masnadi-Shirazi, Hamed and Vasconcelos, Nuno. On the Design of Loss Functions for Classification: theory, robustness to outliers, and SavageBoost. In Advances in Neural Information Processing Systems 21, pp. 1049-1056. 2009.
10. Nock, Richard and Nielsen, Frank. On the efficient minimization of classification calibrated surrogates. In NIPS'08, pp. 1201-1208, 2008.
11. Rosasco, L., De, E., Caponnetto, Vito A., Piana, M., and Verri, A. Are loss functions all the same. Neural Computation, 16(5), 2004.
12. Shalev-Shwartz, S. Online Learning: Theory, Algorithms, and Applications. PhD thesis, The Hebrew University, 2007.
13. Shalev-Shwartz, S., Shamir, O., and Sridharan, K. Learning kernel-based halfspaces with the zero-one loss. Arxiv preprint arXiv: 1005.3681, 2010.
14. Srebro, N., Sridharan, K., and Tewari, A. Smoothness, low noise and fast rates. In NIPS, 2010.
15. Zhang, T. Solving large scale linear prediction problems using stochastic gradient descent algorithms. In Proceedings of the Twenty-First International Conference on Machine Learning, 2004.