Abstract
We study the parameterized complexity of learning k-juntas and some variations of juntas. We show the hardness of learning k-juntas and subclasses of k-juntas in the PAC model by reductions from a W[2]-complete problem. On the other hand, as a consequence of a more general result we show that k-juntas are exactly learnable with improper equivalence queries and access to a W[P] oracle.
Work supported by a DST-DAAD project grant for exchange visits.
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
Almuallim, H., Dietterich, T.G.: Learning boolean concepts in the presence of many irrelevant features. Artificial Intelligence 69(1-2), 279–305 (1994)
Angluin, D.: Learning regular sets from queries and counterexamples. Information and Control 75, 87–106 (1987)
Blum, A.: My favorite open problems (and a few results). In: Talk given at 2001 NeuroCOLT Alpine Workshop on Computational Complexity Aspects of Learning, March 26-29,2001 Sestriere, Italy (2001)
Blum, A.: Learning a function of r relevant variables. In: COLT, pp. 731–733 (2003)
Blum, A., Rudich, S.: Fast learning of k-term DNF formulas with queries. Journal of Computer and System Sciences 51(3), 367–373 (1995)
Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.K.: Occam’s razor. Information Processing Letters 24(6), 377–380 (1987)
Bshouty, N., Cleve, R., Gavaldà, R., Kannan, S., Tamon, C.: Oracles and queries that are sufficient for exact learning. Journal of Computer and System Sciences 52, 421–433 (1996)
Bshouty, N., Tamon, C.: On the fourier spectrum of monotone functions. Journal of the ACM 43(4), 747–770 (1996)
Chvatal, V.: A greedy heuristic for the set covering problem. Mathematics of Operations Research 4(3), 233–235 (1979)
Downey, R.G., Evans, P.A., Fellows, M.R.: Parameterized learning complexity. In: Proc. 6th Annual ACM Conference on Computational Learning Theory, pp. 51–57. ACM Press, New York (1993)
Downey, R.G., Fellows, M.R.: Fixed-parameter tractability and completeness I: Basic results. SIAM Journal on Computing 24(4), 873–921 (1995)
Downey, R.G., Fellows, M.R.: Parameterized Complexity. Springer, Heidelberg (1999)
Fellows, M., Koblitz, N.: Fixed-parameter complexity and cryptography. In: Moreno, O., Cohen, G., Mora, T. (eds.) Proc. Tenth International Symposium on Applied Algebra, Algebraic Algorithms, and Error Correcting Codes. LNCS, vol. 673, pp. 121–131. Springer, Heidelberg (1993)
Flum, J., Grohe, M.: Parameterized Complexity Theory. Springer, Heidelberg (2006)
Haussler, D.: Quantifying inductive bias: AI learning algorithms and Valiant’s learning framework. Artificial Intelligence 36, 177–221 (1988)
Johnson, D.S.: Approximation algorithms for combinatorial problems. Journal of Computer and System Sciences 9, 256–278 (1974)
Kearns, M.J., Vazirani, U.V.: An Introduction to Computational Learning Theory. MIT Press, Cambridge (1994)
Kolountzakis, M., Markakis, E., Mehta, A.: Learning symmetric juntas in time n o(k). Interface between Harmonic Analysis and Number Theory (2005)
Kushilevitz, E., Mansour, Y.: Learning decision trees using the fourier spectrum. SIAM Journal on Computing 22(6), 1331–1348 (1993)
Lipton, R., Markakis, E., Mehta, A., Vishnoi, N.: On the fourier spectrum of symmetric boolean functions with applications to learning symmetric juntas. In: Twentieth Annual IEEE Conference on Computational Complexity, pp. 112–119 (2005)
Littlestone, N.: Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning 2, 285–318 (1988)
Mossel, E., O’Donnell, R., Servedio, R.P.: Learning juntas. In: Proc. 35th ACM Symposium on Theory of Computing, pp. 206–212. ACM Press, New York (2003)
Pitt, L., Valiant, L.G.: Computational limitations on learning from examples. Journal of the ACM 35(4), 965–984 (1988)
Valiant, L., Vazirani, V.: NP is as easy as detecting unique solutions. Theoretical Computer Science 47, 85–93 (1986)
Valiant, L.G.: A theory of the learnable. Communications of the ACM 27(11), 1134–1142 (1984)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arvind, V., Köbler, J., Lindner, W. (2007). Parameterized Learnability of k-Juntas and Related Problems. In: Hutter, M., Servedio, R.A., Takimoto, E. (eds) Algorithmic Learning Theory. ALT 2007. Lecture Notes in Computer Science(), vol 4754. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75225-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-75225-7_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75224-0
Online ISBN: 978-3-540-75225-7
eBook Packages: Computer ScienceComputer Science (R0)