Abstract
k-decision lists and decision trees play important roles in learning theory as well as in practical learning systems, k-decision lists generalize classes such as monomials, k-DNF, and k-CNF and like these subclasses is polynomially PAC-learnable [19]. This leaves open the question of whether k-decision lists can be learned as efficiently as k-DNF. We answer this question negatively in a certain sense, thus disproving a claim in a popular textbook [2]. Decision trees, on the other hand, are not even known to be polynomially PAC-learnable, despite their widespread practical application. We will show that decision trees are not likely to be efficiently PAC-learnable. We summarize our specific results.
The following problems cannot be approximated in polynomial time within a factor of \(2^{\log ^\delta n}\) for any δ<1, unless NP⊂DTIME[2polylog n]: a generalized set cover, k-decision lists, k-decision lists by monotone decision lists, and decision trees. Decision lists cannot be approximated in polynomial time within a factor of n δ, for some constant δ>0, unless NP=P. Also, k-decision lists with l 0–1 alternations cannot be approximated within a factor logl n unless NP⊂DTIME[n O(log log n)] (providing an interesting comparison to the upper bound recently obtained in [1]).
The research was supported by NSERC Research Grants OGP0046613 and OGP-0046506, an NSERC International Fellowship, and ITRC.
Preview
Unable to display preview. Download preview PDF.
References
Aditi Dhagat and Lisa Hellerstein. PAC learning with irrelevant attributes. To appear in Proc. 35rd IEEE Symp. Found. Comp. Sci., 1994.
M. Anthony and N. Biggs. Computational Learning Theory. Cambridge University Press, 1992.
R. Board and L. Pitt, On the necessity of Occam Algorithms. 1990 STOC, pp. 54–63.
A. Arora, C. Lund, R. Motwani, M. Sudan, and M. Szegedy. Proof verification and hardness of approximation problems. Proc. 33rd IEEE Symp. Found. Comp. Sci., 1992, 14–23.
M. Bellare, S. Goldwasser, C. Lund, and A. Russel. Efficient probabilistically checkable proofs and applications to approximation. Proc. 25th ACM Symp. on Theory of Computing, 1993, 294–304.
A. Blumer and A. Ehrenfeucht and D. Haussler and M. Warmuth. Learnability and the Vapnik-Chervonenkis dimension. J. Assoc. Comput. Mach., 35 (1989), 929–965.
L. Breiman, J. Friedman, R. Olshen and C. Stone. Classification and Regression Trees. Wadsworth International Group, Belmont, CA (1984).
A. Ehrenfeucht and D. Haussler. Learning decision trees from random examples. COLT'88.
M. Garey and D. Johnson. Computers and Intractability. Freeman, New York, 1979.
D. Haussler. Quantifying inductive bias: AI learning algorithms and Valiant's learning framework. Artificial Intelligence 36:2 (1988), 177–222.
L. Hyafil and R. Rivest. Constructing optimal decision trees is NP-complete. IPL, 5:1 (1976), 15–17.
M. Kearns, M. Li, L. Pitt, L. Valiant. On the learnability of Boolean functions. Proc. 19th STOC, 1987, New York, 285–295.
C. Lund and M. Yannakakis. On the hardness of approximating minimization problems. Proc. 25th ACM Symp. on Theory of Computing, 1993, 286–293.
J. Mingers. An empirical comparison of selection measures for decision-tree induction. Machine Learning. 3 (1989), 319–342.
J.R. Quinlan. Induction of decision trees. Machine Learning. 1 (1986), 81–106.
J.R. Quinlan and R. Rivest. Inferring decision trees using the minimum description length principle. Inform. Computation, 80 (1989), 227–248.
C.H. Papadimitriou and M. Yannakakis. Optimization, approximation, and complexity classes. Extended abstract in Proc. 20th ACM Symp. on Theory of Computing. 1988, 229–234; full version in Journal of Computer and System Sciences 43, 1991, 425–440.
L. Pitt and L. Valiant. Computational limitations on learning from examples. Journal of the ACM, 35:4 (1988), 965–984.
R. Rivest. Learning decision lists. Machine Learning, 2 (1987), 229–246.
L. Valiant. A theory of the learnable. Communications of the ACM. 27 (1984), 1134–1142.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hancock, T., Jiang, T., Li, M., Tromp, J. (1995). Lower bounds on learning decision lists and trees. In: Mayr, E.W., Puech, C. (eds) STACS 95. STACS 1995. Lecture Notes in Computer Science, vol 900. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59042-0_102
Download citation
DOI: https://doi.org/10.1007/3-540-59042-0_102
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59042-2
Online ISBN: 978-3-540-49175-0
eBook Packages: Springer Book Archive