Minimax predictive density for sparse count data

This paper discusses predictive densities under the Kullback–Leibler loss for high-dimensional Poisson sequence models sparsity constraints. Sparsity in count data implies zero-inflation. We present a class of Bayes that attain asymptotic minimaxity sparse models. also show our with an estimator unknown level plugged-in is adaptive asymptotically minimax sense. For application, we extend results to settings quasi-sparsity and missing-completely-at-random observations. The simulation studies as well application real illustrate efficiency proposed densities.