Generalised Entropies and Asymptotic Complexities of Languages

Research output: Contribution to journalArticlepeer-review

934 Downloads (Pure)

Abstract

In this paper the concept of asymptotic complexity of languages is introduced. This concept formalises the notion of learnability in a particular environment and generalises Lutz and Fortnow’s concepts of predictability and dimension. Then asymptotic complexities in different prediction environments are compared by describing the set of all pairs of asymptotic complexities w.r.t. different environments. A geometric characterisation in terms of generalised entropies is obtained and thus the results of Lutz and Fortnow are generalised.
Original languageEnglish
Pages (from-to)101–141
Number of pages41
JournalInformation and Computation
Volume237
Early online date9 Jan 2014
DOIs
Publication statusPublished - Oct 2014

Cite this