Department of Pattern Recognition

(eng): Barron-type estimators are histogram-based distribution estimators that have been proved to have good consistency properties according to several information theoretic criteria. However they are not continuous. In this paper, we examine a new type estimators with the frequency polygon. We prove the consistency of these estimators in expected information divergence and expected chi-squared-divergence. For one of them we evaluate the rate of convergence in expected chi-squared-divergence.