Mixability is Bayes risk curvature relative to log loss
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...[Show more]
|Collections||ANU Research Publications|
|Source:||Journal of Machine Learning Research|
|01_Van Erven_Mixability_is_Bayes_risk_2012.pdf||419.72 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.