Metraipolis › archive › dc_474248a66faf
Learning Erasing Equal-Length Relational Pattern Languages in the Limit from Positive Data over Binary Alphabets — arXiv:2610.39156
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39156
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:27:06.396Z
- SHA-256 of the archived text
440fdf8d19bab771d10aa0b05d41fe9b16ecb477b1de32fb821c75982555772e- Stable URL of this page
https://metraipolis.com/documento/dc_474248a66faf
How to cite
Learning Erasing Equal-Length Relational Pattern Languages in the Limit from Positive Data over Binary Alphabets — arXiv:2610.39156 — arXiv (en), https://arxiv.org/abs/2610.39156 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_474248a66faf (Metraipolis archive dc_474248a66faf, sha256 440fdf8d19bab771d10aa0b05d41fe9b16ecb477b1de32fb821c75982555772e)
BibTeX
@misc{dc474248a66faf,
title = {Learning Erasing Equal-Length Relational Pattern Languages in the Limit from Positive Data over Binary Alphabets — arXiv:2610.39156},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39156},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_474248a66faf; sha256 440fdf8d19bab771d10aa0b05d41fe9b16ecb477b1de32fb821c75982555772e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39156. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Relational pattern languages generalize Angluin's pattern languages by requiring the strings substituted for repeated occurrences of a variable to stand in a given relation, rather than to be identical. We study erasing pattern languages under the equal-length relation, where all occurrences of a variable must be replaced by strings of the same length. Over alphabets with at least three letters, this class is known to be learnable in the limit from positive data. We show that over a binary alphabet it is not, which resolves an open question from earlier work. Our proof reveals that non-learnability already holds for the restricted subclass of languages generated by patterns that have exactly three maximal substrings of variables. We then show that patterns with at most two maximal substrings of variables are learnable in the limit from positive data for every alphabet of size at least two. If the target pattern is known to have at most one maximal substring of variables, this can even be achieved by an iterative learner, which updates its hypothesis using only the current example and its previous hypothesis. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Logic in Computer Science (cs.LO) ; Formal Languages and Automata Theory (cs.FL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.39156 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-01T02:12:44.287Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).