In this paper, we discuss optimal next-sample prediction for families of probability distributions with a locally compact topological group structure. The right-invariant prior was previously shown to yield a posterior predictive distribution minimizing the worst-case Kullback-Leibler risk among all predictive procedures. However, the assumptions for the proof are so strong that they rarely hold in practice and it is unclear when the density functions used in the proof exist. Therefore, we provide a measure-theoretic proof using a more appropriate set of assumptions. As an application, we show a strong optimality result for next-sample prediction for multivariate normal distributions.
翻译:暂无翻译