On learning read-k-satisfy-j DNF

SIAM Journal on Computing

Volumn 27, Issue 6, 1998, Pages 1515-1530

  Aizenstein, Howard ^a   Blum, Avrim ^b   Khardon, Roni ^c   Kushilevitz, Eyal ^d   Pitt, Leonard ^e   Roth, Dan ^e  

^a UNIVERSITY OF PITTSBURGH   (United States)

^b Carnegie Mellon University   (United States)

^c HARVARD UNIVERSITY   (United States)

^d TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^e University of Illinois at Urbana Champaign   (United States)

Author keywords

Computational learning theory; Decision trees; DNF; Learning

Indexed keywords

ALGORITHMS; COMPUTATION THEORY; DECISION THEORY; EQUIVALENCE CLASSES; MATHEMATICAL MODELS; MEMBERSHIP FUNCTIONS; POLYNOMIALS; PROBABILITY; TREES (MATHEMATICS);

DISJUNCTIVE NORMAL FORM (DNF);

BOOLEAN ALGEBRA;

EID: 0032312992     PISSN: 00975397     EISSN: None     Source Type: Journal    
DOI: 10.1137/S0097539794274398     Document Type: Article

References (38)

1. D. ANGLUIN, M. FRAZIER, AND L. PITT, Learning conjunctions of Horn clauses, Machine Learning, 9 (1992), pp. 147-164.
2. D. ANGLUIN, L. HELLERSTEIN, AND M. KARPINSKI, Learning read-once formulas with queries, J. Assoc. Comput. Mach., 40 (1993), pp. 185-210.
3. H. AIZENSTEIN, L. HELLERSTEIN, AND L. PITT, Read-thrice DNF is hard to learn with membership and equivalence queries, In Proc. 33rd Symp. on the Foundations of Comp. Sci., IEEE Computer Society Press, Los Alamitos, CA, 1992, pp. 523-532. A revised manuscript with additional results will appear in Comput. Complexity, as Aizenstein, Hegedus, Hellerstein, and Pitt, Complexity theoretic hardness results for query learning, to appear.
4. H. AIZENSTEIN, On the Learnability of Disjunctive Normal Form Formulas and Decision Trees, Ph.D. thesis, Dept. of Computer Science, University of Illinois, Urbana, 1993; also Technical Report UIUCDCS-R-93-1813, Dept. of Computer Science, University of Illinois, Urbana, 1993.
5. D. ANGLUIN AND M. KHARITONOV, When won't membership queries help?, J. Comput. System Sci., 50 (1995), pp. 336-355.
6. D. ANGLUIN, Learning k-Term DNF Formulas using Queries and Counterexamples, Technical Report YALEU/DCS/RR-559, Department of Computer Science, Yale University, New Haven, CT, 1987.
7. D. ANGLUIN, Queries and concept learning, Machine Learning, 2 (1988), pp. 319-342.
8. D. ANGLUIN, Negative results for equivalence queries, Machine Learning, 5 (1990), pp. 121-150.
9. H. AIZENSTEIN AND L. PITT, Exact learning of read-twice DNF formulas, In Proc. 32nd IEEE Symp. on Foundations of Computer Science, San Juan, 1991, pp. 170-179.
10. H. AIZENSTEIN AND L. PITT, Exact learning of read-k disjoint DNF and not-so-disjoint DNF, in Proc. Annual ACM Workshop on Computational Learning Theory, Pittsburgh, PA, Morgan Kaufmann, San Francisco, 1992, pp. 71-76.
11. H. AIZENSTEIN AND L. PITT, On the learnability of disjunctive normal form formulas, Machine Learning, 19 (1995), pp. 183-208.
12. A. BLUM, M. FURST, J. JACKSON, M. KEARNS, Y. MANSOUR, AND S. RUDICH, Weakly learning DNF and characterizing statistical query learning using Fourier analysis, In Proc. 26th ACM Symposium on Theory of Computing, ACM, New York, 1994.
13. L. BREIMAN, J. H. FRIEDMAN, R. A. OLSHEN, AND C. J. STONE, Classification and Regression Trees, Wadsworth International Group, CA, 1984.
14. A. BLUM, R. KHARDON, A. KUSHILEVITZ, L. PITT, AND D. ROTH, On learning read-k satisfy-j DNF, in Proc. Annual ACM Workshop on Computational Learning Theory, ACM, New York, 1994, pp. 110-117.
15. A. BLUM AND S. RUDICH, Fast learning of k-term DNF formulas with queries, in Proc. 24th ACM Symposium on Theory of Computing, ACM, New York, 1992, pp. 382-389.
16. A. BLUM AND M. SINGH, Learning functions of k terms, In Proc. COLT '90, Morgan Kaufmann, San Francisco, 1990, pp. 144-153.
17. N. H. BSHOUTY, personal communication, 1994.
18. N. H. BSHOUTY, Exact learning boolean functions via the monotone theory, Inform. and Comput., 123 (1995), pp. 146-153;
19. an earlier version appeared in Proc. 34th Ann. IEEE Symp. on Foundations of Computer Science, 1993.
20. G. GIVATY, personal communication, 1995.
21. T. HANCOCK, Learning 2μ DNF formulas and kμ decision trees, In Proc. 4th Annual Workshop on Computational Learning Theory, Santa Cruz, CA, Morgan Kaufmann, San Francisco, 1991, pp. 199-209.
22. J. JACKSON, An efficient membership-query algorithm for learning DNF with respect to the uniform distribution, in Proc. 35th IEEE Symp. on Foundations of Computer Science, Santa Fe, NM, 1994, pp. 42-53.
23. R. KHARDON, On using the Fourier transform to learn disjoint DNF, Inform. Process. Lett., 49 (1994), pp. 219-222.
24. M. KEARNS, M. LI, L. PITT, AND L. VALIANT, On the learnability of Boolean formulae, In Proc. 19th Annual ACM Symposium on Theory of Computing, ACM, New York, 1987, pp. 285-294.
25. E. KUSHILEVITZ AND Y. MANSOUR, Learning decision trees using the Fourier spectrum, SIAM J. Comput., 22 (1993), pp. 1331-1348;
26. an earlier version appeared in Proc. 23rd Annual ACM Symposium on Theory of Computing, 1991.
27. E. KUSHILEVITZ AND D. ROTH, On learning visual concepts and DNF formulae, Machine Learning, 1 (1995), pp. 11-46;
28. an earlier version appeared in Proc. ACM Workshop on Computational Learning Theory '93, ACM, New York,
29. S. MATAR, Learning with Minimal Number of Queries, Master's thesis, University of Alberta, Canada, 1993.
30. K. PILLAPAKKAMNATT AND V. RAGHAVAN, On the limits of proper learnability of subsets of DNF formulas, in Proc. Annual ACM Workshop on Computational Learning Theory, ACM, New York, 1994, pp. 118-129;
31. Machine Learning, 25 (1996), pp. 237-263.
32. K. PILLAPAKKAMNATT AND V. RAGHAVAN, Read twice DNF formulas are properly learnable, Inform. and Comput., 122 (1995), pp. 236-267.
33. L. PITT AND L. VALIANT, Computational limitations on learning from examples, J. Assoc. Comput. Mach., 35 (1988), pp. 965-984.
34. J. R. QUINLAN, Induction of decision trees, Machine Learning, 1 (1986), pp. 81-106.
35. J. R. QUINLAN, C4.5: Programs for machine learning, Morgan Kaufmann, San Francisco, 1993.
36. H. U. SIMON, A tight Ω(log log n)-bound on the time for parallel RAM's to compute nondegenerate boolean functions, in Lecture Notes in Computer Science 158, Springer-Verlag, New York, 1983, pp. 439-444.
37. L. G. VALIANT, A theory of the learnable, Comm. ACM, 27 (1984), pp. 1134-1142.
38. L. G. VALIANT, Learning disjunctions of conjunctions, in Proc. 9th International Joint Conference on Artificial Intelligence, Vol. 1, Los Angeles, CA, 1985, pp. 560-566.