Asymmetric team learning

Abstract

We generalize the traditional concept of team learning. The success of an asymmetric team in learning some function depends upon the successes of participant machines by an arbitrary nondecreasing Boolean function. Asymmetric team types are ordered accordingly to their learning power by basic reductions. The problem to determine this order for an arbitrary pair of asymmetric teams is shown to be NP-hard. Basic reductions are independent of the properties of any particular definition of learning. Many learning types (e.g. EXn - learning with no more than n mind-changes) have additional team order relations which vary from case to case. We define a learning type PINFIN which allows only the basic reductions between its teams. The relation between asymmetric team learning and probabilistic learning is described by a zero-sum matrix game.