Skip to main content

On the Complexity of Learning Programs

  • Conference paper
  • First Online:
Unity of Logic and Computation (CiE 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13967))

Included in the following conference series:

  • 254 Accesses

Abstract

Given a computable sequence of natural numbers, it is a natural task to find a Gödel number of a program that generates this sequence. It is easy to see that this problem is neither continuous nor computable. In algorithmic learning theory this problem is well studied from several perspectives and one question studied there is for which sequences this problem is at least learnable in the limit. Here we study the problem on all computable sequences and we classify the Weihrauch complexity of it. For this purpose we can, among other methods, utilize the amalgamation technique known from learning theory. As a benchmark for the classification we use closed and compact choice problems and their jumps on natural numbers, which correspond to induction and boundedness principles, as they are known from the Kirby-Paris hierarchy in reverse mathematics. We provide a topological as well as a computability-theoretic classification, which reveal some significant differences.

Vasco Brattka is supported by the National Research Foundation of South Africa.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 54.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 69.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bishop, E.: Foundations of Constructive Analysis. McGraw-Hill, New York (1967)

    MATH  Google Scholar 

  2. Brattka, V.: Stashing-parallelization pentagons. Logic. Methods Comput. Sci. 17(4), 1–29 (2021). https://doi.org/10.46298/lmcs-17(4:20)2021

  3. Brattka, V.: The discontinuity problem. J. Symb. Logic (2022). https://doi.org/10.1017/jsl.2021.106

  4. Brattka, V.: On the complexity of computing Gödel numbers. arXiv 2302.04213 (2023). https://arxiv.org/abs/2302.04213

  5. Brattka, V., de Brecht, M., Pauly, A.: Closed choice and a uniform low basis theorem. Ann. Pure Appl. Logic 163, 986–1008 (2012). https://doi.org/10.1016/j.apal.2011.12.020

    Article  MathSciNet  MATH  Google Scholar 

  6. Brattka, V., Gherardi, G.: Effective choice and boundedness principles in computable analysis. Bull. Symb. Log. 17(1), 73–117 (2011). https://doi.org/10.2178/bsl/1294186663

    Article  MathSciNet  MATH  Google Scholar 

  7. Brattka, V., Gherardi, G., Marcone, A.: The Bolzano-Weierstrass theorem is the jump of weak Kőnig’s lemma. Ann. Pure Appl. Logic 163, 623–655 (2012). https://doi.org/10.1016/j.apal.2011.10.006

    Article  MathSciNet  MATH  Google Scholar 

  8. Brattka, V., Gherardi, G., Pauly, A.: Weihrauch complexity in computable analysis. In: Handbook of Computability and Complexity in Analysis. TAC, pp. 367–417. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-59234-9_11

    Chapter  MATH  Google Scholar 

  9. Brattka, V., Pauly, A.: On the algebraic structure of Weihrauch degrees. Logic. Methods Comput. Sci. 14(4:4), 1–36 (2018). https://lmcs.episciences.org/4918

  10. Brattka, V., Rakotoniaina, T.: On the uniform computational content of Ramsey’s theorem. J. Symb. Log. 82(4), 1278–1316 (2017). https://doi.org/10.1017/jsl.2017.43

    Article  MathSciNet  MATH  Google Scholar 

  11. Dzhafarov, D.D., Mummert, C.: Reverse Mathematics. Theory and Applications of Computability. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-11367-3

  12. Dzhafarov, D.D., Solomon, R., Yokoyama, K.: On the first-order parts of problems in the Weihrauch degrees. arXiv 2301.12733 (2023). https://arxiv.org/abs/2301.12733

  13. Freivald, R.V., Wiehagen, R.: Inductive inference with additional information. Elektron. Inform. Kybernetik 15(4), 179–185 (1979)

    MathSciNet  MATH  Google Scholar 

  14. Gauthier, T., Olšák, M., Urban, J.: Alien coding. arXiv 2301.11479 (2023). https://arxiv.org/abs/2301.11479

  15. 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

    Article  MathSciNet  MATH  Google Scholar 

  16. Hájek, P., Pudlák, P.: Metamathematics of First-Order Arithmetic. Perspectives in Mathematical Logic. Springer-Verlag, Berlin (1993). https://doi.org/10.1007/978-3-662-22156-3

  17. Hirschfeldt, D.R.: Slicing the truth: on the computable and reverse mathematics of combinatorial principles. Lecture Notes Series, Institute for Mathematical Sciences, National University of Singapore, vol. 28. World Scientific, Singapore (2015). http://www.worldscientific.com/worldscibooks/10.1142/9208

  18. Hoyrup, M., Rojas, C.: On the information carried by programs about the objects they compute. Theory Comput. Syst. 61(4), 1214–1236 (2016). https://doi.org/10.1007/s00224-016-9726-9

    Article  MathSciNet  MATH  Google Scholar 

  19. Neumann, E., Pauly, A.: A topological view on algebraic computation models. J. Complexity 44(Supplement C), 1–22 (2018). http://www.sciencedirect.com/science/article/pii/S0885064X17300766

  20. Odifreddi, P.: Classical Recursion Theory - Volume II, Studies in Logic and the Foundations of Mathematics, vol. 143. North-Holland, Amsterdam (1999)

    Google Scholar 

  21. Osherson, D.N., Stob, M., Weinstein, S.: Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists. MIT Press, Cambridge, MA (1990)

    Google Scholar 

  22. Simpson, S.G.: Subsystems of Second Order Arithmetic, 2nd edn. Perspectives in Logic, Cambridge University Press (2009)

    Book  MATH  Google Scholar 

  23. Soldà, G., Valenti, M.: Algebraic properties of the first-order part of a problem. Annal. Pure Appl. Logic 174, 103270 (2023). https://doi.org/10.1016/j.apal.2023.103270

  24. Valenti, M.: A journey through computability, topology and analysis, Ph. D. thesis, Universitá degli Studi di Udine (2021)

    Google Scholar 

  25. Westrick, L.: A note on the diamond operator. Computability 10(2), 107–110 (2021). https://doi.org/10.3233/COM-200295

    Article  MathSciNet  MATH  Google Scholar 

  26. Wiehagen, R.: Zur Theorie der Algorithmischen Erkennung. Dissertation B, Humboldt-Universität zu Berlin (1978)

    Google Scholar 

  27. Zeugmann, T., Zilles, S.: Learning recursive functions: a survey. Theoret. Comput. Sci. 397(1–3), 4–56 (2008). https://doi.org/10.1016/j.tcs.2008.02.021

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Vasco Brattka .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Brattka, V. (2023). On the Complexity of Learning Programs. In: Della Vedova, G., Dundua, B., Lempp, S., Manea, F. (eds) Unity of Logic and Computation. CiE 2023. Lecture Notes in Computer Science, vol 13967. Springer, Cham. https://doi.org/10.1007/978-3-031-36978-0_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-36978-0_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-36977-3

  • Online ISBN: 978-3-031-36978-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics