Are Loss Functions All the Same?

Neural Computation

Volumn 16, Issue 5, 2004, Pages 1063-1076

  Rosasco, Lorenzo ^a   De Vito, Ernesto ^b,c   Caponnetto, Andrea ^a   Piana, Michele ^a   Verri, Alessandro ^a  

^a UNIVERSITY OF GENOA   (Italy)

^b UNIVERSITY OF MODENA AND REGGIO EMILIA   (Italy)

^c INFN SEZIONE DI GENOVA   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; BIOLOGICAL MODEL; LEARNING; PHYSIOLOGY; STATISTICAL MODEL; STATISTICS;

LEARNING; LINEAR MODELS; MODELS, NEUROLOGICAL; STATISTICS;

EID: 1842733197     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976604773135104     Document Type: Article

References (18)

1. Alon, N., Ben-David, S., Cesa-Bianchi, N., & Haussler, D. (1993). Scale-sensitive dimensions,uniform convergence and learnability. In Proceedings of the 34th Annual IEEE Conference on Foundations of Computer Science (pp. 292-301). New York: IEEE.
2. Aronszajn, N. Theory of reproducing kernels. (1950). Trans. Amer. Math. Soc., 686, 337-404.
3. Cristianini, N., & Shawe Taylor, J. (2000). An introduction to support vector machines. Cambridge: Cambridge University Press.
4. Cucker, F., & Smale, S. (2002). Best choices for regularization parameters in learning theory: On the bias-variance problem. Foundation of Computational Mathematics, 2, 413-428.
5. Cucker, F., & Smale, S. (2002). On the mathematical foundation of learning. Bull. A.M.S., 39, 1-49.
6. Evgeniou, T., Pontil, M., & Poggio, T. (2000). Regularization networks and support vector machines. Adv. Comp. Math., 13, 1-50.
7. Girosi, F., Jones, M., & Poggio, T. (1995). Regularization theory and neural networks architectures. Neural Computation, 7, 219-269.
8. Hastie, T., Tibshirani, R., & Friedman, J. (2001). The elements of statistical learning. New York: Springer-Verlag.
9. Lin, G., Wahba, Y., Zhang, H., & Lee, Y. (2003). Statistical properties and adaptive tuning of support vector machines. Machine Learning, 48, 115-136.
10. Lugosi, G., & Vayatis, N. (in press). On the Bayes risk consistency of regularized boosting methods. Annals of Statistics.
11. Pontil, M. (in press). A note on different covering numbers in learning theory. J. Complexity.
12. Rockafellar, R. (1970). Convex analysis. Princeton, NJ: Princeton University Press.
13. Rosasco, L., De Vito, E., Caponnetto, A., Piana, M., & Verri. (2003). Notes on the use of different loss functions (Tech. Rep. No. DISI-TR-03-07). Genova: Department of Computer Science, University of Genova, Italy.
14. Vapnik, V. (1995). The nature of statistical learning theory. New York: Springer-Verlag.
15. Vapnik, V. (1998). Statistical learning theory. New York: Wiley.
16. Wahba, G. (1990). Splines models for observational data. Philadelphia: SIAM.
17. Zhang, T. (in press). Statistical behavior and consistency of classification methods based on convex risk minimization. Annals of Statistics.
18. Zhou, D. (2002). The covering number in learning theory. J. Complexity, 18, 739-767.