Complexity theoretic hardness results for query learning

Computational Complexity

Volumn 7, Issue 1, 1998, Pages 19-53

  Aizenstein, Howard ^a   Hegedus, Tibor ^c   Hellerstein, Lisa ^b   Pitt, Leonard ^d  

^a UNIVERSITY OF PITTSBURGH   (United States)

^b NORTHWESTERN UNIVERSITY   (United States)

^c Physics and Informatics   (Slovakia)

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

Author keywords

Complexity theory; Computational learning theory; Equivalence queries; Membership queries; Query learning; Read thrice DNF; Threshold functions

Indexed keywords

EID: 0032361270     PISSN: 10163328     EISSN: None     Source Type: Journal    
DOI: 10.1007/PL00001593     Document Type: Article

References (63)

1. H. AIZENSTEIN, On the Learnability of Disjunctive Normal Form Formulas and Decision Trees. PhD thesis, Department of Computer Science, University of Illinois at Urbana-Champaign, Technical report UIUCDCS-R-93-1813, Urbana, IL, June 1993.
2. H. AIZENSTEIN, A. BLUM, R. KHARDON, E. KUSHILEVITZ, L. PITT, AND D. ROTH, On learning read-k-satisfy-j DNF. To appear, SIAM Journal on Computing. Preliminary version appears in Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, ACM Press, New York, July 1994, 110-117.
3. H. AIZENSTEIN, A. BLUM, R. KHARDON, E. KUSHILEVITZ, L. PITT, AND D. ROTH, On learning read-k-satisfy-j DNF. To appear, SIAM Journal on Computing. Preliminary version appears in Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, ACM Press, New York, July 1994, 110-117.
4. H. AIZENSTEIN, L. HELLERSTEIN, AND L. PITT, Read-thrice DNF is hard to learn with membership and equivalence queries. In Proceedings of the 33rd Annual IEEE Symposium on Foundations of Computer Science, IEEE Computer Society Press, Los Alamitos, CA, 1992, 523-532.
5. D. ANGLUIN, Learning k-term DNF formulas using queries and counterexamples. Technical Report YALE/DCS/RR-559, Department of Computer Science, Yale University, New Haven, CT, August 1987.
6. D. ANGLUIN, Learning regular sets from queries and counterexamples. Information and Computation 75:2 (1987), 87-106.
7. D. ANGLUIN, Queries and concept learning. Machine Learning 2:4 (1988), 319-342.
8. D. ANGLUIN, Negative results for equivalence queries. Machine Learning 5:2 (1990), Special Issue on Computational Learning Theory, 121-150.
9. D. ANGLUIN, Computational learning theory: survey and selected bibliography. In Proceedings of the Twenty-fourth Annual ACM Symposium on the Theory of Computing, ACM Press, New York, 1992, 351-369.
10. D. ANGLUIN, Exact learning of μ-DNF formulas with malicious membership queries. Technical Report YALEU/DCS/TR-1020, Department of Computer Science, Yale University, New Haven, CT, March 1994.
11. D. ANGLUIN, M. FRAZIER, AND L. PITT, Learning conjunctions of Horn clauses. Machine Learning 9:2/3 (1992), 147-164.
12. D. ANGLUIN, L. HELLERSTEIN, AND M. KARPINSKI, Learning read-once formulas with queries. Journal of the ACM 40:1 (1993), 185-210.
13. D. ANGLUIN AND M. KHARITONOV, When won't membership queries help? Journal of Computer and System Sciences 50 (1995). Preliminary version appears in Proceedings of the Twenty-third Annual ACM Symposium on the Theory of Computing, ACM Press, New York, May 1991, 444-454.
14. D. ANGLUIN AND M. KHARITONOV, When won't membership queries help? Journal of Computer and System Sciences 50 (1995). Preliminary version appears in Proceedings of the Twenty-third Annual ACM Symposium on the Theory of Computing, ACM Press, New York, May 1991, 444-454.
15. A. BLUM, Separating distribution-free and mistake-bound learning models over the Boolean domain. SIAM Journal on Computing 23:5 (1994), 990-1000.
16. A. BLUM AND R. L. RIVEST, Training a 3-node neural net is NP-Complete. In Advances in Neural Information Processing Systems I, Morgan Kaufmann, San Mateo, CA, 1989, 494-501.
17. A. BLUM AND M. SINGH, Learning functions of k terms. In Proceedings of the Third Annual Workshop on Computational Learning Theory, Morgan Kaufmann, San Mateo, CA, 1990, 144-153.
18. A. BLUMER, A. EHRENFEUCHT, D. HAUSSLER, AND M. WARMUTH, Learnability and the Vapnik-Chervonenkis dimension. Journal of the ACM 36:4 (1989), 929-965.
19. A. BLUMER, A. EHRENFEUCHT, D. HAUSSLER, AND M. WARMUTH, Occam's razor. Information Processing Letters 24 (1987), 377-380.
20. R. BOARD AND L. PITT, On the necessity of Occam algorithms. Theoretical Computer Science 100 (1992), 157-184.
21. N. BSHOUTY, Exact learning via the monotone theory. In Proceedings of the 34th Annual IEEE Symposium on Foundations of Computer Science, IEEE Computer Society Press, Los Alamitos, CA, 1993, 302-311 .
22. N. BSHOUTY, R. CLEVE, S. KANNAN, AND C. TAMON, Oracles and queries that are sufficient for exact learning. In Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, ACM Press, New York, 1994, 130-137.
23. N. BSHOUTY, T. HANCOCK, AND L. HELLERSTEIN, Learning arithmetic read-once formulas. SIAM Journal on Computing 24:4 (1995), 706-735.
24. N. BSHOUTY, T. HANCOCK, AND L. HELLERSTEIN, Learning boolean read-once formulas over generalized bases. Journal of Computer and System Sciences 50:3 (1995), 521-542.
25. N. BSHOUTY, T. HANCOCK, L. HELLERSTEIN, AND M. KARPINSKI, An algorithm to learn read-once threshold formulas, and transformations between learning models. Computational Complexity 4 (1994), 37-61.
26. V. CHVATAL AND P. L. HAMMER, Aggregation of inequalities in integer programming. Annals of Discrete Mathematics 1 (1977), 145-162.
27. B. DASGUPTA, H. T. SIEGELMANN, AND E. SONTAG, On a learnability question associated to neural networks with continuous activations. In Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, ACM Press, New York, 1994, 47-56.
28. P. FISCHER AND H. U. SIMON, On learning ring-sum-expansions. SIAM Journal on Computing 21:1 (1992), 181-192.
29. RICARD GAVALDÀ, The complexity of learning via queries. In Proceedings of the Ninth Structure in Complexity Theory Conference, IEEE Computer Society Press, Los Alamitos, CA, 1994, 324-337.
30. M. C. GOLUMBIC, Algorithmic Graph Theory and Perfect Graphs. Academic Press, New York, 1980.
31. V. A. GURVICH, On repetition-free boolean functions. Uspekhi Mat. Nauk 32 (1977), 183-184.
32. P. L. HAMMER, T. IBARAKI, AND U. N. PELED, Threshold Numbers and Threshold Completions. North Holland, Amsterdam, 1981, 125-145.
33. D. HAUSSLER, Learning conjunctive concepts in structural domains. Machine Learning 4:1 (1989), 7-40.
34. T. HEGEDUS, Can complexity theory benefit from learning theory? (extended abstract). In Proceedings of the European Conference on Machine Learning, volume LNCS667 (subseries LNAI), Springer Verlag, Berlin, 1993, 354-359.
35. T. HEGEDUS, On training simple neural networks and small-weight neurons. In Computational Learning Theory: Eurocolt '93, New Series Number 533 (The Institute of Mathematics and its Applications Conference Series), Oxford University Press, Oxford, 1994, 69-82.
36. T. HEGEDUS, Generalized teaching dimensions and the query complexity of learning. In Proceedings of the Eighth Annual ACM Conference on Computational Learning Theory, ACM Press, New York, 1995, 108-117.
37. L. HELLERSTEIN, On characterizing and learning some classes of read-once functions. PhD Thesis, U.C. Berkeley, 1989.
38. L. HELLERSTEIN, K. PILLAIPAKKAMNATT, V. RAGHAVAN, AND D. WILKINS, How many queries are needed to learn? In Proceedings of the Twenty-seventh Annual ACM Symposium on the Theory of Computing, ACM Press, New York, 1995, 190-199. To appear, Journal of the ACM.
39. chunk class of synchronizing primitives. SIAM Journal on Computing (1977), 88-108.
40. H. ISHIZAKA, Polynomial time learnability of simple deterministic languages. Machine Learning 5:2 (1990), 151-164.
41. J. JACKSON, An efficient membership-query algorithm for learning DNF with respect to the uniform distribution. In Proceedings of the 35th Annual IEEE Symposium on Foundations of Computer Science, IEEE Computer Society Press, Los Alamitos, CA, 1994, 42-53.
42. S. JUDD, Learning in neural networks. In Proceedings of the First Annual Workshop on Computational Learning Theory, Morgan Kaufmann, San Mateo, CA, 1988, 2-8.
43. M. KARCHMER, N. LINIAL, I. NEWMAN, M. SAKS, AND A. WIGDERSON, Combinatorial characterization of read-once formulae. Discrete Mathematics 114 (1993), 275-282.
44. M. KEARNS, M. LI, L. PITT, AND L. G. VALIANT, On the learnability of Boolean formulae. In Proceedings of the Nineteenth Annual ACM Symposium on the Theory of Computing, ACM Press, New York, 1987, 285-294.
45. M. KEARNS AND L. G. VALIANT, Cryptographic limitations on learning Boolean formulae and finite automata. Journal of the ACM 41:1 (1994), 67-95.
46. 2-Complete problems in computational learning theory. Preprint, 1991.
47. J-H. LIN AND J. S. VITTER, Complexity results on learning by neural networks. Machine Learning 6:3 (1991), 211-230.
48. W. MAASS AND GY. TURÁN, Algorithms and lower bounds for on-line learning of geometrical concepts. Machine Learning 14:3 (1994), 251-269.
49. W. MAASS AND GY. TURÁN, How fast can a threshold gate learn? In Computational Learning Theory and Natural Learning Systems: Constraints and Prospects, ed. S. HANSON, G. DRASTAL, AND R. RIVEST, MIT Press, Cambridge, MA, 1994, 381-414.
50. S. MUROGA, Threshold logic and its applications. Wiley-Interscience, 1971.
51. K. PILLAIPAKKAMNATT AND V. RAGHAVAN, Read-twice DNF formulas are properly learnable. In Computational Learning Theory: Eurocolt '93, New Series Number 53 (The Institute of Mathematics and its Applicaations Conference Series), Oxford University Press, Oxford, 1994, 121-132.
52. K. PILLAIPAKKAMNATT AND V. RAGHAVAN, On the limits of proper learnability of subclasses of DNF formulas. In Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, ACM Press, New York, 1994, 118-129.
53. L. PITT AND L. G. VALIANT, Computational limitations on learning from examples. Journal of the ACM 35:4 (1988), 965-984.
54. L. PITT AND M. K. WARMUTH, The minimum consistent DFA problem cannot be approximated within any polynomial. Journal of the ACM 40:1 (1993), 95-142.
55. L. PITT AND M. K. WARMUTH, Prediction preserving reducibility. Journal of Computer and System Sciences 41:3 (1990), 430-467.
56. V. RAGHAVAN AND S. SCHACH, Learning switch configurations. In Proceedings of the Third Annual Workshop on Computational Learning Theory, Morgan Kaufmann, San Mateo, CA, 1990, 38-51.
57. P. D. SEYMOUR, A note on the production of matroid minors. Journal of Combinatorial Theory (B) (1977), 289-295.
58. L. J. STOCKMEYER, The polynomial-time hierarchy. Theoretical Computer Science 3 (1976), 1-22.
59. L. J. STOCKMEYER AND A. R. MEYER, Word problems requiring exponential time. In Proceedings of the Fifth Annual ACM Symposium on the Theory of Computing, ACM Press, New York, 1973, 1-9.
60. R. I. TYSHKEVICH AND A. A. CHERNYAK, Threshold decompositions of boolean functions and graphs. In Combinatorial-Algebraic and Probabilistic Methods of Discrete Analysis, Gorkii University, 1989, 111-129.
61. L. G. VALIANT, A theory of the learnable. Communications of the ACM 27:11 (1984), 1134-1142.
62. C. WRATHALL, Complete sets for the polynomial time hierarchy. Theoretical Computer Science 3 (1976), 23-34.
63. M. YANNAKAKIS, The complexity of the partial order dimension problem. SIAM Journal on Algebraic and Discrete Methods 3:3 (1982) 351-358.