On convergence of information contained in quantized observations

0410875 20240103182245.520060210235959.9 On convergence of information contained in quantized observations 10 s. cav_un_epca*02567230018-9448IEEE Transactions on Information Theory488 (2002)2163-2172Institute of Electrical and Electronics Engineers convergence of quantized information Csiszar divergences generalized Fisher information cav_un_auth*0101218 Vajda Igor UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. 09J GA201/02/1391 GA ČR cav_un_auth*0000526 CEZ:AV0Z1075907 By the well-known information processing theorem, quantization of observations reduce values of convex information functionals such as the information divergence, Fisher information, or Shannon information. This paper deals with the convergence of the reduced values of these inctions to their original unreduced values of various sequences of partitions of the observations space. BD SI http://hdl.handle.net/11104/0130962 UTIA-B 20020089 2002 cav_un_epca*0256723 IEEE Transactions on Information Theory 0018-9448 1557-9654 Roč. 48 č. 8 2002 2163 2172 Institute of Electrical and Electronics Engineers