We study the problem of learning the probability distribution of a multinomial variable from an observed sequence of signals, starting in a condition of ignorance about this distribution. We show that not all signals are suited for producing non-vacuous inferences under prior ignorance. To...

Consider a relaxed multinomial setup, in which there may be mistakes in observing the outcomes of the processthis is often the case in real applications. What can we say about the next outcome if we start learning about the process in conditions of prior ignorance? To answer this question we...