Minimax Optimal Bayes Mixtures for Memoryless Sources over Large Alphabets

Elias Jääsaari, Janne Leppä-aho, Tomi Silander, Teemu Roos

Abstract: The normalized maximum likelihood (NML) distribution achieves minimax log loss and coding regret for the multinomial model. In practice other nearly minimax distributions are used instead as calcul...