Mixability is Bayes Risk Curvature Relative to Log Loss - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of Machine Learning Research Year : 2012

Mixability is Bayes Risk Curvature Relative to Log Loss

Abstract

Mixability of a loss characterizes fast rates in the online learning setting of prediction with expert advice. The determination of the mixability constant for binary losses is straightforward but opaque. In the binary case we make this transparent and simpler by characterising mixability in terms of the second derivative of the Bayes risk of proper losses. We then extend this result to multiclass proper losses where there are few existing results. We show that mixability is governed by the maximum eigenvalue of the Hessian of the Bayes risk, relative to the Hessian of the Bayes risk for log loss. We conclude by comparing our result to other work that bounds prediction performance in terms of the geometry of the Bayes risk. Although all calculations are for proper losses, we also show how to carry the results across to improper losses.
Fichier principal
Vignette du fichier
vanerven12a.pdf (419.72 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-00758204 , version 1 (28-11-2012)

Identifiers

  • HAL Id : hal-00758204 , version 1

Cite

Tim van Erven, Mark D. Reid, Robert C. Williamson. Mixability is Bayes Risk Curvature Relative to Log Loss. Journal of Machine Learning Research, 2012, 13, pp.1639−1663. ⟨hal-00758204⟩
206 View
145 Download

Share

Gmail Facebook X LinkedIn More