English

Classifying different criteria for learning algebraic structures

Logic 2024-10-31 v1

Abstract

In the last years there has been a growing interest in the study of learning problems associated with algebraic structures. The framework we use models the scenario in which a learner is given larger and larger fragments of a structure from a given target family and is required to output an hypothesis about the structure's isomorphism type. So far researchers focused on Ex\mathbf{Ex}-learning, in which the learner is asked to eventually stabilize to the correct hypothesis, and on restrictions where the learner is allowed to change the hypothesis a fixed number of times. Yet, other learning paradigms coming from classical algorithmic learning theory remained unexplored. We study the "learning power" of such criteria, comparing them via descriptive-set-theoretic tools thanks to the novel notion of EE-learnability. The main outcome of this paper is that such criteria admit natural syntactic characterizations in terms of infinitary formulas analogous to the one given for Ex\mathbf{Ex}-learning in [6]. Such characterizations give a powerful method to understand whether a family of structure is learnable with respect to the desired criterion.

Keywords

Cite

@article{arxiv.2410.22933,
  title  = {Classifying different criteria for learning algebraic structures},
  author = {Nikolay Bazhenov and Vittorio Cipriani and Sanjay Jain and Luca San Mauro and Frank Stephan},
  journal= {arXiv preprint arXiv:2410.22933},
  year   = {2024}
}
R2 v1 2026-06-28T19:41:02.798Z