Abstract
We adapt the classical notion of learning from text to computable structure theory. Our main result is a model-theoretic characterization of the learnability from text for classes of structures. We show that a family of structures is learnable from text if and only if the structures can be distinguished in terms of their theories restricted to positive infinitary \(\varSigma _2\) sentences.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ash, C.J., Knight, J.F.: Computable Structures and the Hyperarithmetical Hierarchy. Studies in Logic and the Foundations of Mathematics, vol. 144. Elsevier Science B.V. (2000)
Bazhenov, N.A., Ganchev, H., Vatev, S.: Computable embeddings for pairs of linear orders. Algebra Logic 60(3), 163–187 (2021). https://doi.org/10.1007/s10469-021-09639-7
Bazhenov, N., Cipriani, V., San Mauro, L.: Learning algebraic structures with the help of Borel equivalence relations. Theor. Comput. Sci. 951 (2023). https://doi.org/10.1016/j.tcs.2023.113762
Bazhenov, N., Fokina, E., Rossegger, D., Soskova, A.A., Vatev, S.V.: A Lopez-Escobar theorem for continuous domains (2023). http://arxiv.org/abs/2301.09940
Bazhenov, N., Fokina, E., San Mauro, L.: Learning families of algebraic structures from informant. Inf. Comput. 275, 104590 (2020). https://doi.org/10.1016/j.ic.2020.104590
Bazhenov, N., San Mauro, L.: On the Turing complexity of learning finite families of algebraic structures. J. Log. Comput. 31(7), 1891–1900 (2021). https://doi.org/10.1093/logcom/exab044
Calvert, W., Cummins, D., Knight, J.F., Miller, S.: Comparing classes of finite structures. Algebra Logic 43(6), 374–392 (2004). https://doi.org/10.1023/B:ALLO.0000048827.30718.2c
Case, J.: Enumeration reducibility and partial degrees. Ann. Math. Logic 2(4), 419–439 (1971). https://doi.org/10.1016/0003-4843(71)90003-9
Cooper, S.B.: Enumeration reducibility, nondeterministic computations and relative computability of partial functions. In: Ambos-Spies, K., Müller, G.H., Sacks, G.E. (eds.) Recursion Theory Week. LNM, vol. 1432, pp. 57–110. Springer, Heidelberg (1990). https://doi.org/10.1007/BFb0086114
Fokina, E., Kötzing, T., San Mauro, L.: Limit learning equivalence structures. In: Garivier, A., Kale, S. (eds.) Proceedings of the 30th International Conference on Algorithmic Learning Theory. Proceedings of Machine Learning Research, vol. 98, pp. 383–403. PMLR (2019)
Gao, Z., Stephan, F., Wu, G., Yamamoto, A.: Learning families of closed sets in matroids. In: Dinneen, M.J., Khoussainov, B., Nies, A. (eds.) WTCS 2012. LNCS, vol. 7160, pp. 120–139. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27654-5_10
Gold, E.M.: Language identification in the limit. Inf. Control 10(5), 447–474 (1967). https://doi.org/10.1016/S0019-9958(67)91165-5
Harizanov, V.S., Stephan, F.: On the learnability of vector spaces. J. Comput. Syst. Sci. 73(1), 109–122 (2007). https://doi.org/10.1016/j.jcss.2006.09.001
Jain, S., Osherson, D., Royer, J.S., Sharma, A.: Systems that Learn. MIT Press, Cambridge (1999)
Knight, J.F., Miller, S., Vanden Boom, M.: Turing computable embeddings. J. Symb. Log. 72(3), 901–918 (2007). https://doi.org/10.2178/jsl/1191333847
Martin, E., Osherson, D.: Scientific discovery on positive data via belief revision. J. Philos. Log. 29(5), 483–506 (2000). https://doi.org/10.1023/A:1026569206678
Putnam, H.: Trial and error predicates and the solution to a problem of Mostowski. J. Symb. Log. 30(1), 49–57 (1965). https://doi.org/10.2307/2270581
Soskov, I.: Degree spectra and co-spectra of structures. Ann. Sofia Univ. 96, 45–68 (2004)
Stephan, F., Ventsov, Y.: Learning algebraic structures from text. Theor. Comput. Sci. 268(2), 221–273 (2001). https://doi.org/10.1016/S0304-3975(00)00272-3
Acknowledgements
The work of Bazhenov was supported by the Russian Science Foundation (project no. 24-11-00227). Fokina was supported by the Austrian Science Fund FWF through the project P 36781. Rossegger was supported by the European Union’s Horizon 2020 Research and Innovation Programme under the Marie Skłodowska-Curie grant agreement No. 101026834—ACOSE. Soskova was supported by the European Union-NextGenerationEU, through the National Recovery and Resilience Plan of the Republic of Bulgaria, project no. BG-RRP-2.004-0008-C01. Vatev was supported by FNI-SU 80-10-180/17.05.2023.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bazhenov, N., Fokina, E., Rossegger, D., Soskova, A., Vatev, S. (2024). Learning Families of Algebraic Structures from Text. In: Levy Patey, L., Pimentel, E., Galeotti, L., Manea, F. (eds) Twenty Years of Theoretical and Practical Synergies. CiE 2024. Lecture Notes in Computer Science, vol 14773. Springer, Cham. https://doi.org/10.1007/978-3-031-64309-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-64309-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-64308-8
Online ISBN: 978-3-031-64309-5
eBook Packages: Computer ScienceComputer Science (R0)