Abstract
Sample compression schemes are schemes for “encoding” a set of examples in a small subset of examples. The long-standing open sample compression conjecture states that, for any concept class \(\mathcal{C}\) of VC-dimension d, there is a sample compression scheme in which samples for concepts in \(\mathcal{C}\) are compressed to samples of size at most d.
We show that every order over \(\mathcal{C}\) induces a special type of sample compression scheme for \(\mathcal{C}\), which we call order compression scheme. It turns out that order compression schemes can compress to samples of size at most d if \(\mathcal{C}\) is maximum, intersection-closed, a Dudley class, or of VC-dimension 1–and thus in most cases for which the sample compression conjecture is known to be true.
Since order compression schemes are much simpler than sample compression schemes in general, their study seems to be a promising step towards resolving the sample compression conjecture. We reveal a number of fundamental properties of order compression schemes, which are helpful in such a study. In particular, order compression schemes exhibit interesting graph-theoretic properties as well as connections to the theory of learning from teachers.
This work was partly supported by the Natural Sciences and Engineering Research Council of Canada (NSERC).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Littlestone, N., Warmuth, M.K.: Relating data compression and learnability. Technical report, University of California at Santa Cruz (1986)
Floyd, S., Warmuth, M.K.: Sample compression, learnability, and the Vapnik-Chervonenkis dimension. Machine Learning 21(3), 269–304 (1995)
Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.K.: Learnability and the Vapnik-Chervonenkis dimension. Journal of the ACM 36(4), 929–965 (1989)
Ben-David, S., Litman, A.: Combinatorial variability of Vapnik-Chervonenkis classes with applications to sample compression schemes. Discrete Applied Mathematics 86, 3–25 (1998)
Doliwa, T., Fan, G., Simon, H.U., Zilles, S.: Recursive teaching dimension, VC-dimension, and sample compression (submitted, January 2013)
Doliwa, T., Simon, H.U., Zilles, S.: Recursive teaching dimension, learning complexity, and maximum classes. In: Hutter, M., Stephan, F., Vovk, V., Zeugmann, T. (eds.) ALT 2010. LNCS (LNAI), vol. 6331, pp. 209–223. Springer, Heidelberg (2010)
Kuzmin, D., Warmuth, M.K.: Unlabeled compression schemes for maximum classes. Journal of Machine Learning Research 8, 2047–2081 (2007)
Rubinstein, B.I., Rubinstein, J.H.: A geometric approach to sample compression. Journal of Machine Learning Research 13, 1221–1261 (2012)
Sauer, N.: On the density of families of sets. J. Comb. Theory, Ser. A 13(1), 145–147 (1972)
Welzl, E.: Complete range spaces (1987) (unpublished manuscript)
Dudley, R.M.: A course on empirical processes. Lecture Notes in Mathematics 1097, 1–142 (1984)
Zilles, S., Lange, S., Holte, R., Zinkevich, M.: Models of cooperative teaching and learning. Journal of Machine Learning Research 12, 349–384 (2011)
Goldman, S.A., Kearns, M.J.: On the complexity of teaching. Journal of Computer and System Sciences 50(1), 20–31 (1995)
Shinohara, A., Miyano, S.: Teachability in computational learning. New Generation Computing 8(4), 337–347 (1991)
Fan, G.: A graph-theoretic view of teaching. M.Sc. Thesis, University of Regina (2012)
Natarajan, B.K.: On learning boolean functions. In: Proceedings of the 19th Annual Symposium on Theory of Computing, pp. 296–304 (1987)
Helmbold, D.P., Sloan, R.H., Warmuth, M.K.: Learning nested differences of intersection-closed concept classes. Machine Learning 5, 165–196 (1990)
Alpaydin, E.: Introduction to Machine Learning, 2nd edn. MIT Press (2010)
Welzl, E., Wöginger, G.: On Vapnik-Chervonenkis dimension one (1987) (unpublished manuscript)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Darnstädt, M., Doliwa, T., Simon, H.U., Zilles, S. (2013). Order Compression Schemes. In: Jain, S., Munos, R., Stephan, F., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2013. Lecture Notes in Computer Science(), vol 8139. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40935-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-40935-6_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40934-9
Online ISBN: 978-3-642-40935-6
eBook Packages: Computer ScienceComputer Science (R0)