In this paper we investigate the impact of choosing different loss functions from the viewpoint of statistical learning theory. We introduce a convexity assumption - which is met by all loss functions commonly used in the literature, and study how the bound on the estimation error changes with the loss. We also derive a general result on the minimizer of the expected risk for a convex loss function in the case of classification. The main outcome of our analysis is that, for classification, the hinge loss appears to be the loss of choice. Other things being equal, the hinge loss leads to a convergence rate practically indistinguishable from the logistic loss rate and much better than the square loss rate. Furthermore, if the hypothesis space is sufficiently rich, the bounds obtained for the hinge loss are not loosened by the thresholding stage.

Are Loss Functions All the Same?

ROSASCO, LORENZO;DE VITO, ERNESTO;PIANA, MICHELE;VERRI, ALESSANDRO
2004-01-01

Abstract

In this paper we investigate the impact of choosing different loss functions from the viewpoint of statistical learning theory. We introduce a convexity assumption - which is met by all loss functions commonly used in the literature, and study how the bound on the estimation error changes with the loss. We also derive a general result on the minimizer of the expected risk for a convex loss function in the case of classification. The main outcome of our analysis is that, for classification, the hinge loss appears to be the loss of choice. Other things being equal, the hinge loss leads to a convergence rate practically indistinguishable from the logistic loss rate and much better than the square loss rate. Furthermore, if the hypothesis space is sufficiently rich, the bounds obtained for the hinge loss are not loosened by the thresholding stage.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/248819
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 328
  • ???jsp.display-item.citation.isi??? 258
social impact