Lower bounds to moments of list size

Abstract

Summary form only given. The list-size random variable L for a block code is defined as the number of incorrect messages that appear to a maximum-likelihood decoder to be at least as likely as the true message. Lower bounds to the moments of L have been obtained. For sequential decoding, the results imply that the tth moment of computation is unbounded at rates above a certain value, for all t≥0, and settle a long-standing open problem.