Maximization of the information divergence from multinomial distributions

SUMMARY Explicit solution of the problem of maximization of information divergence from the family of multinomial distribu-tions is presented. General problem of maximization of information divergence from an exponential family has emerged in probabilistic models for evolution and learning in neural networks, based on infomax principles. The maximizers admit interpretation as stochastic systems with high complexity w.r.t. exponential family.