Home Learning of monotone functions with single error correction
Article
Licensed
Unlicensed Requires Authentication

Learning of monotone functions with single error correction

  • Svetlana N. Selezneva EMAIL logo and Yongqing Liu
Published/Copyright: June 25, 2021

Abstract

Learning of monotone functions is a well-known problem. Results obtained by V. K. Korobkov and G. Hansel imply that the complexity φM(n) of learning of monotone Boolean functions equals Cnn/2 + Cnn/2+1 (φM(n) denotes the least number of queries on the value of an unknown monotone function on a given input sufficient to identify an arbitrary n-ary monotone function). In our paper we consider learning of monotone functions in the case when the teacher is allowed to return an incorrect response to at most one query on the value of an unknown function so that it is still possible to correctly identify the function. We show that learning complexity in case of the possibility of a single error is equal to the complexity in the situation when all responses are correct.


Note: Originally published in Diskretnaya Matematika (2019) 31, №4, 53–69 (in Russian).


  1. Funding: Research was partially supported by RFBR, project 19-01-00200-a.

References

[1] Korobkov V. K., “On monotone functions of the algebra logic”, Problemy kibernetiki, 1965, N 13, 5–28 (in Russian).Search in Google Scholar

[2] Korobkov V. K., “An estimate of the number of monotone functions of an algebra of logic and the complexity of the algorithm of finding the resolvent set for an aribitrary function of the algebra logic”, Dokl. Akad. Nauk SSSR, 150:4 (1963), 744–747 (in Russian).Search in Google Scholar

[3] Hansel G., “Sur le nombre des fonctions Booleennes monotones de n variables”, C. R. Acad. Sci. Paris, 262 (1966), 1088–1090.Search in Google Scholar

[4] Alekseev V. B., “On the deciphering some classes of monotone multivalued functions”, 16:1 (1976), 189–198 (in Russian).10.1016/0041-5553(76)90083-5Search in Google Scholar

[5] Sapozhenko A. A., Goryainov M. V., “On decoding monotone functions on partially ordered sets”, Diskretnyy analiz i issle-dovanie operatsiy, 2:3 (1995), 79–80 (in Russian).Search in Google Scholar

[6] Sapozhenko A. A., Dedekind’s problem and the method of boundary functionals, M.: Fizmatlit, 2009 (in Russian), 152 pp.Search in Google Scholar

[7] Damaschke P., “Adaptive versus nonadaptive attribute-efficient learning”, Machine Learning, 41 (2000), 197–215.10.1145/276698.276874Search in Google Scholar

[8] Osokin V. V., “On learning monotone Boolean functions with irrelevant variables”, Discrete Math. Appl., 20:3 (2010), 307–320.10.1515/dma.2010.018Search in Google Scholar

[9] Bshouty N.H., “Exact learning from an honest teacher that answers membership queries”, Theor. Comput. Sci., 733 (2018), 4–43.10.1016/j.tcs.2018.04.034Search in Google Scholar

[10] Korobkov V. K., “On some integer linear programming problems”, Problemy kibernetiki, 1965, №14, 297–299 (in Russian).Search in Google Scholar

Received: 2019-07-22
Revised: 2019-11-07
Published Online: 2021-06-25
Published in Print: 2021-06-25

© 2021 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 10.10.2025 from https://www.degruyterbrill.com/document/doi/10.1515/dma-2021-0017/html
Scroll to top button