Dynamically Delayed Postdictive Completeness and Consistency in Learning

Abstract

In computational function learning in the limit, an algorithmic learner tries to find a program for a computable function g given successively more values of g , each time outputting a conjectured program for g . A learner is called postdictively complete iff all available data is correctly postdicted by each conjecture. Akama and Zeugmann presented, for each choice of natural number δ , a relaxation to postdictive completeness: each conjecture is required to postdict only all except the last δ seen data points. This paper extends this notion of delayed postdictive completeness from constant delays to dynamically computed delays. On the one hand, the delays can be different for different data points. On the other hand, delays no longer need to be by a fixed finite number, but any type of computable countdown is allowed, including, for example, countdown in a system of ordinal notations and in other graphs disallowing computable infinitely descending counts. We extend many of the theorems of Akama and Zeugmann and provide some feasible learnability results. Regarding fairness in feasible learning, one needs to limit use of tricks that postpone output hypotheses until there is enough time to “think” about them. We see, for polytime learning, postdictive completeness (and delayed variants): 1. allows some but not all postponement tricks, and 2. there is a surprisingly tight boundary, for polytime learning, between what postponement is allowed and what is not. For example : 1. the set of polytime computable functions is polytime postdictively completely learnable employing some postponement, but 2. the set of exptime computable functions, while polytime learnable with a little more postponement, is not polytime postdictively completely learnable! We have that, for w a notation for ω , the set of exptime functions is polytime learnable with w-delayed postdictive completeness. Also provided are generalizations to further, small constructive limit ordinals.