Chen, Hubie and Valeriote, M. (2019) Learnability of solutions to conjunctive queries. Journal of Machine Learning Research 20 (67), pp. 1-28. ISSN 1532-4435.
![[img]](https://eprints.bbk.ac.uk/style/images/fileicons/text.png) |
Text
learnabilityTrichotomy.pdf - Author's Accepted Manuscript Restricted to Repository staff only Download (328kB) |
|
|
Text
27755.pdf - Published Version of Record Available under License Creative Commons Attribution. Download (406kB) | Preview |
Abstract
The problem of learning the solution space of an unknown formula has been studied inmultiple embodiments in computational learning theory. In this article, we study a familyof such learning problems; this family contains, for each relational structure, the problem oflearning the solution space of an unknown conjunctive query evaluated on the structure. Aprogression of results aimed to classify the learnability of each of the problems in this family,and thus far a culmination thereof was a positive learnability result generalizing all previousones. This article completes the classification program towards which this progression ofresults strived, by presenting a negative learnability result that complements the mentionedpositive learnability result. In addition, a further negative learnability result is exhibited,which indicates a dichotomy within the problems to which the first negative result applies.In order to obtain our negative results, we make use of universal-algebraic concepts.
Metadata
| Item Type: | Article |
|---|---|
| Keyword(s) / Subject(s): | concept learning, computational learning theory, dichotomy theorems, re-ductions, universal algebra |
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences |
| Depositing User: | Hubie Chen |
| Date Deposited: | 10 Jun 2019 09:08 |
| Last Modified: | 09 Aug 2023 12:46 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/27755 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
