Alpha-NML Universal Predictors

02/25/2022
by   Marco Bondaschi, et al.
0

Inspired by Sibson's alpha-mutual information, we introduce a new class of universal predictors that depend on a real parameter greater than one. This class interpolates two well-known predictors, the mixture estimator, that includes the Laplace and the Krichevsky-Trofimov predictors, and the Normalized Maximum Likelihood (NML) estimator. We point out some advantages of this class of predictors and study its performance in terms of known regret measures under logarithmic loss, in particular for the well-studied case of discrete memoryless sources.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset