Abstract
Programs over semigroups are a well-studied model of computation for boolean functions. It has been used successfully to characterize, in algebraic terms, classes of problems that can, or cannot, be solved within certain resources. The interest of the approach is that the algebraic complexity of the semigroups required to capture a class should be a good indication of its expressive (or computing) power. In this paper we derive algebraic characterizations for some “small” classes of boolean functions, all of which have depth-3 AC0 circuits, namely k-term DNF, k-DNF, k-decision lists, decision trees of bounded rank, and DNF. The interest of such classes, and the reason for this investigation, is that they have been intensely studied in computational learning theory.
Partially supported by the IST Programme of the EU under contract number IST-1999-14186 (ALCOM-FT), by the Spanish Government TIC2001-1577-C03-02 (LOGFAC), by CIRIT 1997SGR-00366, and TIC2000-1970-CE.
Supported by NSERC, FCAR, and the von Humboldt Foundation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D. Angluin. Learning regular sets from queries and counterexamples. Information and Computation, 75:87–106, 1987.
D. Angluin. Queries and concept learning. Machine Learning, 2:319–342, 1988.
D.A. Barrington. Bounded-width polynomial-size branching programs recognize exactly those languages in NC1. Journal of Computer and System Sciences, 38:150–164, 1989.
A.L. Blum. Rank-r decision trees are a subclass of r-decision lists. Information Processing Letters, 42:183–185, 1992.
M. Beaudry, P. McKenzie, and D. Thérien. The membership problem in aperiodic transformation monoids. Journal of the ACM, 39(3):599–616, 1992.
A. Blum and S. Rudich. Fast learning of k-term dnf formulas with queries. Journal of Computer and System Sciences, 51:367–373, 1995.
N.H. Bshouty. Exact learning boolean functions via the monotone theory. Information and Computation, 123:146–153, 1995.
D.A. Mix Barrington, H. Straubing, and D. Thérien. Non-uniform automata over groups. Information and Computation, 89:109–132, 1990.
D.A. Mix Barrington and D. Thérien. Finite monoids and the fine structure of NC1. Journal of the ACM, 35:941–952, 1988.
J. Castro and J.L. Balcázar. Simple PAC learning of simple decision lists. In Algorithmic Learning Theory, 6th International Workshop, ALT’ 95, Proceedings, volume 997, pages 239–248. Springer, 1995.
A. Ehrenfeucht and D. Haussler. Learning decision trees from random examples. Information and Computation, 82:231–246, 1989.
S. Eilenberg. Automata, Languages, and Machines, volume B. Academic Press, 1976.
T. Elomaa. The biases of decision tree pruning strategies. In Advances in Intelligent Data Analysis: Proc. 3rd Intl. Symp., pages 63–74, 1999.
R. Gavaldà, D. Thérien, and P. Tesson. Learning expressions and programs over monoids. In Technical Report R01-38, Department LSI, UPC, pages-, 2001.
J.C. Jackson. An efficient membership-query algorithm for learning dnf. Journal of Computer and System Sciences, 53:414–440, 1997.
M.J. Kearns and U.V. Vazirani. An Introduction to Computational Learning Theory. The MIT Press, 1994.
A. Maciel, P. Péladeau, and D. Thérien. Programs over semigroups of dotdepth one. Theoretical Computer Science, 245:135–148, 2000.
Ronald L. Rivest. Learning decision lists. Machine Learning, 2(3):229–246, 1987.
J.-F. Raymond, P. Tesson, and D. Thérien. An algebraic approach to communication complexity. In Proc. ICALP’98, Springer-Verlag LNCS, volume 1443, pages 29–40, 1998.
M.P. Schützenberger. Sur le produit de concaténation non ambigu. Semigroup Forum, 13:47–75, 1976.
H.U. Simon. Learning decision lists and trees with equivalence queries. In Proceedings of the 2nd European Conference on Computational Learning Theory (EuroCOLT’95), pages 322–336, 1995.
M. Szegedy. Functions with bounded symmetric communication complexity, programs over commutative monoids, and acc. Journal of Computer and System Sciences, 47:405–423, 1993.
D. Thérien. Programs over aperiodic monoids. Theoretical Computer Science, 64(3):271–280, 29 1989.
D. Thérien and P. Tesson. Diamonds are forever: the DA variety. In submitted, 2001.
L.G. Valiant. A theory of the learnable. Communications of the ACM, 27:1134–1142, 1984.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gavaldà, R., Thérien, D. (2003). Algebraic Characterizations of Small Classes of Boolean Functions. In: Alt, H., Habib, M. (eds) STACS 2003. STACS 2003. Lecture Notes in Computer Science, vol 2607. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36494-3_30
Download citation
DOI: https://doi.org/10.1007/3-540-36494-3_30
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00623-7
Online ISBN: 978-3-540-36494-8
eBook Packages: Springer Book Archive