Consistency versus realizable H-consistency for multiclass classification

30th International Conference on Machine Learning, ICML 2013

Volumn , Issue PART 3, 2013, Pages 1838-1846

  Long, Philip M ^a   Servedio, Rocco A ^b  

^a MICROSOFT   (United States)

^b Department of Earth and Environmental Sciences   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE BOOSTING; ALGORITHMS; LEARNING SYSTEMS;

BAYES-OPTIMAL; CLASSIFICATION ACCURACY; EXPECTED LOSS; LINEARLY SEPARABLE; LOSS FUNCTIONS; MULTI-CLASS CLASSIFICATION; POSITIVE CONSTANT; SCORING FUNCTIONS;

CLASSIFICATION (OF INFORMATION);

EID: 84897489038     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. Ben-David, S., Loker, D., Srebro, N., and Sridharan, K. Minimizing the misclassification error rate using a surrogate convex loss. In ICML, 2012.
2. Bottou, L. Large-scale machine learning with stochastic gradient descent. In Proceedings of the 19th International Conference on Computational Statistics (COMPSTAT'2010), pp. 177-187, 2010.
3. Breiman, L. Some infinity theory for predictor ensembles. Annals of Statistics, 32(1):1-11, 2004.
4. Crammer, K. and Singer, Y. On the algorithmic implementation of multiclass kernel-based vector machines. JMLR, 2:265-292, 2001.
5. Friedman, J., Hastie, T., and Tibshirani, R. Additive logistic regression: A statistical view of boosting. The Annals of Statistics, 38(2):337-407, 2000. (Pubitemid 33227445)
6. Harchaoui, Zaïd, Douze, Matthijs, Paulin, Mattis, Dudík, Miroslav, and Malick, Jérôme. Large-scale image classification with trace-norm regularization. In CVPR, pp. 3386-3393, 2012.
7. Haussler, D. Decision theoretic generalizations of the PAC model for neural net and other learning applications. Information and Computation, 100(1): 78-150, 1992.
8. Kearns, M. J., Schapire, R. E., and Sellie, L. M. Toward efficient agnostic learning. Proceedings of the 1992 Workshop on Computational Learning Theory, pp. 341-352, 1992.
9. Lee, Y., Lin, Y., and Wahba, G. Multicategory support vector machines: Theory and application to the classification of microarray data and satellite radiance data. Journal of the American Statistical Association, 99(465):67-81, 2004. (Pubitemid 38545195)
10. Lin, Y., Lv, F., Zhu, S., Yang, M., Cour, T., Yu, K., Cao, L., and Huang, T. Large-scale image classification: fast feature extraction and SVM training. In CVPR, pp. 1689-1696, 2011.
11. Liu, Y. Fisher consistency of multicategory support vector machines. In UAI, pp. 291-298, 2007.
12. Long, P. M. and Servedio, R. A. Random classification noise defeats all convex potential boosters. Machine Learning, 78(3):287-304, 2010.
13. Perronnin, F., Akata, Z., Harchaoui, Z., and Schmid, C. Towards good practice in large-scale learning for image classification. CVPR, pp. 3482-3489, 2012.
14. Polyak, B. T. and Juditsky, A. B. Acceleration of stochastic approximation by averaging. SIAM J. Control Optim., 30(4):838-855, 1992.
15. Tewari, A. and Bartlett, P. L. On the consistency of multiclass classification methods. JMLR, 8:1007-1025, 2007. (Pubitemid 46798410)
16. Vapnik, V. N. Inductive principles of the search for empirical dependences (methods based on weak convergence of probability measures). Proceedings of the 1989 Workshop on Computational Learning Theory, 1989.
17. Weston, J., Bengio, S., and Usunier, N. Large scale image annotation: learning to rank with joint word-image embeddings. Machine Learning, 81(1):21-35, 2010.
18. Xu, W. Towards optimal one pass large scale learning with averaged stochastic gradient descent. Arxiv, 2011.
19. Zhang, T. Statistical analysis of some multi-category large margin classification methods. Journal of Machine Learning Research, 5:1225-1251, 2004.