Mixability is Bayes Risk Curvature Relative to Log Loss.

Tim van Erven Mark D. Reid Robert C. Williamson

Published in: J. Mach. Learn. Res. (2012)

Keyphrases

bayes risk
upper and lower bounds
loss function
reproducing kernel hilbert space
approximation error
distortion measure
posterior probability
vector quantizer
regularization parameter
squared error
lower bound
optimal solution
real valued
multiscale
vector quantization