Abstract
In order to systematize existing results, we propose to analyze the learnability of boolean functions computed by an algebraically defined model, programs over monoids. The expressiveness of the model, hence its learning complexity, depends on the algebraic structure of the chosen monoid. We identify three classes of monoids that can be identified, respectively, from Membership queries alone, Equivalence queries alone, and both types of queries. The algorithms for the first class are new to our knowledge, while those for the other two are combinations or particular cases of known algorithms. Learnability of these three classes captures many previous learning results. Moreover, by using nontrivial taxonomies of monoids, we can argue that using the same techniques to learn larger classes of boolean functions seems to require proving new circuit lower bounds or proving learnability of DNF formulas.
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
Almeida, J., Margolis, S.W., Steinberg, B., Volkov, M.V.: Representation theory of finite semigroups, semigroup radicals and formal language theory. Trans. Amer. Math. Soc. 3612, 1429–1461 (2009)
Almeida, J., Margolis, S.W., Volkov, M.V.: The pseudovariety of semigroups of triangular matrices over a finite field. RAIRO - Theoretical Informatics and Applications 39(1), 31–48 (2005)
Angluin, D.: Learning regular sets from queries and counterexamples. Information and Computation 75, 87–106 (1987)
Angluin, D.: Queries and concept learning. Machine Learning 2, 319–342 (1988)
Barrington, D.A.: Bounded-width polynomial-size branching programs recognize exactly those languages in NC1. Journal of Computer and System Sciences 38, 150–164 (1989)
Beimel, A., Bergadano, F., Bshouty, N.H., Kushilevitz, E., Varricchio, S.: Learning functions represented as multiplicity automata. Journal of the ACM 47, 506–530 (2000)
Bergadano, F., Bshouty, N.H., Tamon, C., Varricchio, S.: On learning branching programs and small depth circuits. In: Ben-David, S. (ed.) EuroCOLT 1997. LNCS, vol. 1208, pp. 150–161. Springer, Heidelberg (1997)
Blum, A., Chalasani, P., Jackson, J.C.: On learning embedded symmetric concepts. In: COLT, pp. 337–346 (1993)
Bhshouty, N.H., Kushilevitz, E.: Learning from membership queries / online learning. Course notes in N. Bshouty’s homepage
Mix Barrington, D.A., Straubing, H., Thérien, D.: Non-uniform automata over groups. Information and Computation 89, 109–132 (1990)
Beigel, R., Tarui, J.: On ACC. Computational Complexity 4, 350–366 (1994)
Bergadano, F., Varricchio, S.: Learning behaviors of automata from multiplicity and equivalence queries. SIAM Journal on Computing 25, 1268–1280 (1996)
Chattopadhyay, A., Goyal, N., Pudlák, P., Thérien, D.: Lower bounds for circuits with mod m gates. In: FOCS, pp. 709–718 (2006)
Chattopadhyay, A., Krebs, A., Koucký, M., Szegedy, M., Tesson, P., Thérien, D.: Languages with bounded multiparty communication complexity. In: Thomas, W., Weil, P. (eds.) STACS 2007. LNCS, vol. 4393, pp. 500–511. Springer, Heidelberg (2007)
Ehrenfeucht, A., Haussler, D.: Learning decision trees from random examples. Information and Computation 82(3), 231–246 (1989)
Gavaldà, R., Thérien, D.: Algebraic characterizations of small classes of boolean functions. In: Alt, H., Habib, M. (eds.) STACS 2003. LNCS, vol. 2607, pp. 331–342. Springer, Heidelberg (2003)
Gavaldà, R., Tesson, P., Thérien, D.: Learning expressions and programs over monoids. Inf. Comput. 204(2), 177–209 (2006)
Hellerstein, L., Servedio, R.A.: On pac learning algorithms for rich boolean function classes. Theor. Comput. Sci. 384(1), 66–76 (2007)
Helmbold, D.P., Sloan, R.H., Warmuth, M.K.: Learning nested differences of intersection-closed concept classes. Machine Learning 5, 165–196 (1990)
Kearns, M.J., Li, M., Pitt, L., Valiant, L.G.: On the learnability of boolean formulae. In: STOC, pp. 285–295 (1987)
Klivans, A.R., Shpilka, A.: Learning restricted models of arithmetic circuits. Theory of Computing 2(1), 185–206 (2006)
Kushilevitz, E.: A simple algorithm for learning o(log n)-term dnf. Inf. Process. Lett. 61(6), 289–292 (1997)
Péladeau, P., Thérien, D.: Sur les langages reconnus par des groupes nilpotents. Compte-rendus de l’Académie des Sciences de Paris, 93–95 (1988); Translation to English as ECCC-TR01-040, Electronic Colloquium on Computational Complexity (ECCC)
Rivest, R.L.: Learning decision lists. Machine Learning 2(3), 229–246 (1987)
Schützenberger, M.P.: Sur le produit de concaténation non ambigu. Semigroup Forum 13, 47–75 (1976)
Sherstov, A.A.: Communication lower bounds using dual polynomials. Bulletin of the EATCS 95, 59–93 (2008)
Simon, H.-U.: Learning decision lists and trees with equivalence-queries. In: Vitányi, P.M.B. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 322–336. Springer, Heidelberg (1995)
Tesson, P.: Computational Complexity Questions Related to Finite Monoids and Semigroups. PhD thesis, School of Computer Science, McGill University (2003)
Tesson, P., Thérien, D.: Monoids and computations. Intl. Journal of Algebra and Computation 14(5-6), 801–816 (2004)
Tesson, P., Thérien, D.: Complete classifications for the communication complexity of regular languages. Theory Comput. Syst. 38(2), 135–159 (2005)
Tesson, P., Thérien, D.: Bridges between algebraic automata theory and complexity. Bull. of the EATCS 88, 37–64 (2006)
Valiant, L.G.: A theory of the learnable. Communications of the ACM 27, 1134–1142 (1984)
Weil, P.: Closure of varieties of languages under products with counter. J. of Comp. Syst. Sci. 2(3), 229–246 (1987)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gavaldà, R., Thérien, D. (2009). An Algebraic Perspective on Boolean Function Learning. In: Gavaldà, R., Lugosi, G., Zeugmann, T., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2009. Lecture Notes in Computer Science(), vol 5809. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04414-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-04414-4_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04413-7
Online ISBN: 978-3-642-04414-4
eBook Packages: Computer ScienceComputer Science (R0)