Languages with Decidable Learning: A Meta-theorem (Video, OOPSLA1 2023)
Paul Krogmeier and P. Madhusudan
(University of Illinois at Urbana-Champaign, USA; University of Illinois at Urbana-Champaign, USA)
Abstract: We study expression learning problems with syntactic restrictions and introduce the class of finite-aspect checkable languages to characterize symbolic languages that admit decidable learning. The semantics of such languages can be defined using a bounded amount of auxiliary information that is independent of expression size but depends on a fixed structure over which evaluation occurs. We introduce a generic programming language for writing programs that evaluate expression syntax trees, and we give a meta-theorem that connects such programs for finite-aspect checkable languages to finite tree automata, which allows us to derive new decidable learning results and decision procedures for several expression learning problems by writing programs in the programming language.
Article: [ Ссылка ]
ORCID: [ Ссылка ], [ Ссылка ]
Video Tags: exact learning, learning symbolic languages, tree automata, version space algebra, program synthesis, interpretable learning, oopslaa23main-p28-p, doi:10.1145/3586032, orcid:0000-0002-6710-9516, orcid:0000-0002-9782-721X
Presentation at the OOPSLA1 2023 conference, October 22–27, 2023, [ Ссылка ]
Sponsored by ACM SIGPLAN,
