Duality Between Likelihood Maximization and Shannon Entropy Maximization in Bayesian Prediction

DOI Web Site

Bibliographic Information

Other Title
  • Bayes予測における尤度最大化とShannon entropy最大化の双対性
  • Bayes ヨソク ニ オケル ユウド サイタイカ ト Shannon entropy サイタイカ ノ ソウツイセイ

Search this article

Abstract

We formulate a risk minimization problem in Bayesian prediction in the framework of Bayesian model averaging. Goodness of prediction is evaluated by adopting the dual Kullback-Leibler divergence losses. Duality between likelihood maximization and Shannon entropy maximization is revealed through that of the divervence losses.

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top