Document Open Access Logo

Applications of Littlestone Dimension to Query Learning and to Compression

Authors Hunter Chase , James Freitag , Lev Reyzin

PDF

File

Thumbnail PDF
PDF
LIPIcs.MFCS.2024.42.pdf
  • Filesize: 0.64 MB
  • 10 pages

Document Identifiers

Related Versions

Subject Classification

ACM Subject Classification
  • Theory of computation → Query learning
  • Theory of computation → Randomness, geometry and discrete structures
  • Mathematics of computing → Combinatoric problems
Keywords
  • compression scheme
  • query learning
  • random queries
  • Littlestone dimension

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Abstract

In this paper we give several applications of Littlestone dimension. The first is to the model of [Angluin and Dohrn, 2017], where we extend their results for learning by equivalence queries with random counterexamples. Second, we extend that model to infinite concept classes with an additional source of randomness. Third, we give improved results on the relationship of Littlestone dimension to classes with extended d-compression schemes, proving the analog of a conjecture of [Floyd and Warmuth, 1995] for Littlestone dimension.

Cite As Get BibTex

Hunter Chase, James Freitag, and Lev Reyzin. Applications of Littlestone Dimension to Query Learning and to Compression. In 49th International Symposium on Mathematical Foundations of Computer Science (MFCS 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 306, pp. 42:1-42:10, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024) https://doi.org/10.4230/LIPIcs.MFCS.2024.42

Author Details

Hunter Chase
  • Department of Mathematics, Statistics, and Computer Science, University of Illinois at Chicago, IL, USA
James Freitag
  • Department of Mathematics, Statistics, and Computer Science, University of Illinois at Chicago, IL, USA
Lev Reyzin
  • Department of Mathematics, Statistics, and Computer Science, University of Illinois at Chicago, IL, USA

Funding

This research was supported in part by award ECCS-2217023 from the National Science Foundation and National Science Foundation CAREER award 1945251.

Acknowledgements

The authors wish to thank Shai Ben-David for comments on an early draft.

References

  1. Dana Angluin and Tyler Dohrn. The power of random counterexamples. In International Conference on Algorithmic Learning Theory, pages 452-465, 2017. Google Scholar
  2. Shai Ben-David and Ami Litman. Combinatorial variability of Vapnik-Chervonenkis classes with applications to sample compression schemes. Discrete Applied Mathematics, 86(1):3-25, 1998. Google Scholar
  3. Hunter Chase and James Freitag. Model theory and machine learning. Bulletin of Symbolic Logic, 25(3):319-332, 2019. Google Scholar
  4. Sally Floyd and Manfred Warmuth. Sample compression, learnability, and the Vapnik-Chervonenkis dimension. Machine learning, 21(3):269-304, 1995. Google Scholar
  5. Vincent Guingona. NIP theories and computational learning theory. URL: https://tigerweb.towson.edu/vguingona/NIPTCLT.pdf.
  6. Hunter R Johnson and Michael C Laskowski. Compression schemes, stable definable families, and o-minimal structures. Discrete & Computational Geometry, 43(4):914-926, 2010. Google Scholar
  7. Akash Kumar, Yuxin Chen, and Adish Singla. Teaching via best-case counterexamples in the learning-with-equivalence-queries paradigm. Advances in Neural Information Processing Systems, 34:26897-26910, 2021. Google Scholar
  8. Dima Kuzmin and Manfred K Warmuth. Unlabeled compression schemes for maximum classes. Journal of Machine Learning Research, 8(9), 2007. Google Scholar
  9. Nick Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2(4):285-318, 1988. Google Scholar
  10. Nick Littlestone and Manfred Warmuth. Relating data compression and learnability. Technical report, University of California, Santa Cruz, 1986. Google Scholar
  11. Shay Moran and Amir Yehudayoff. Sample compression schemes for VC classes. Journal of the ACM (JACM), 63(3):21, 2016. Google Scholar
  12. Manfred K. Warmuth. Compressing to vc dimension many points. In Bernhard Schölkopf and Manfred K. Warmuth, editors, Learning Theory and Kernel Machines, pages 743-744, Berlin, Heidelberg, 2003. Springer Berlin Heidelberg. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact