On Bias Plus Variance

Abstract
: This paper presents a Bayesian additive "correction" to the familiar quadratic loss biasplus-variance formula. It then discusses some other loss-function-specific aspects of supervisedlearning. It ends by presenting a version of the bias-plus-variance formula appropriate for log loss,and then the Bayesian additive correction to that formula. Both the quadratic loss and log loss correctionterms are a covariance, between the learning algorithm and the posterior distribution overtargets....

This publication has 3 references indexed in Scilit: