Upper bound on the distribution of computation of a sequential decoder for multiple-access channels

The computational distribution of sequential decoding for discrete memoryless multiple-access channels is examined. It is shown that all possible collections of incorrect paths in the code tree may be described by bipartite graphs. Using this fact and a new decoding metric it is proved that the number of computations in the first incorrect subtree is a Paretean random variable, and that the parameter of the Pareto distribution is estimated similarly to the parameter for systems of information transmission with one source.