Noise-Tolerant Parallel Learning of Geometric Concepts

Information and Computation

Volumn 147, Issue 1, 1998, Pages 89-110

  Bshouty, Nader H ^c   Goldman, Sally A ^a   Mathias, H David ^b  

^a WASHINGTON UNIVERSITY   (United States)

^b OHIO STATE UNIVERSITY   (United States)

^c NONE

Author keywords

Computational learning theory; Geometric concepts; Parallel computation

Indexed keywords

EID: 0242691961     PISSN: 08905401     EISSN: None     Source Type: Journal    
DOI: 10.1006/inco.1998.2737     Document Type: Article

References (41)

1. Angluin, D. (1988), Queries an concept learning, Mach. Learning 2(4), 319-342.
2. Angluin, D., and Laird, P. (1988), Learning from noisy examples, Mach. Learning 2(4), 343-370.
3. Aslam, J. A., and Decatur, S. E. (Nov. 1993), General bounds on statistical query learning and PAC learning with noise via hypothesis boosting, in "34th Annual Symposium on Foundations of Computer Science," pp. 282-291.
4. Aslam, J. A., and Decatur, S. E. (July 1995), Specification and simulation of statistical query algorithms for efficiency and noise tolerance, in "Proceedings of the eighth Annual ACM conference on Computational Learning Theory," pp. 437-446.
5. Auer, P. (July 1995), On-line learning of rectangles in noisy environments, in "Proceedings of the Sixth Annual ACM conference on Computational Learning Theory," pp. 253-261.
6. Balcázar, J. L., Díaz, J., Gavaldà, R., and Watanabe, O. (1994), An optimal parallel algorithm for learning DFA, in "Proceedings of the Seventh Annual ACM conference on Computational Learning Theory," pp. 208-217, ACM Press, New York.
7. Baum, E. B. (1990), On learning a union of half spaces, J. Complexity 6(1), 607-101.
8. Baum, E. B. (1990), The perceptron algorithm is fast for nonmalicious distributions, Neural Computation 2, 248-260.
9. Berger, B., Rompel, J., and Shor, P. W. (1994), Efficient NC algorithms for set cover with applications to learning and geometry, J. Comput. System Sci. 49(2), 454-477.
10. Blum, A. L., and Rivest, R. L. (1992), Training a 3-node neural network is NP-Complete, Neural Networks 5, 117-127.
11. Blumer, A., Ehrenfeucht, A., Haussler, D., and Warmuth, M. K. (1989), Learnability and the Vapnik-Chervonenkis dimension, J. Assoc. Comput. Mach. 36(4), 929-965.
12. Bshouty, N. H., Chen, Z., and Homer, S. (Nov. 1994), On learning discretized geometric concepts, in "35th Annual Symposium on Foundations of Computer Science," pp. 54-63.
13. Bshouty, N. H., and Cleve, R. (Oct. 1992), On the exact learning of formulas in parallel, in "33rd Annual Symposium on Foundations of Computer Science," pp. 1-15.
14. Bshouty, N. H., Goldberg, P. W., Goldman, S. A., and Mathias, H. D. (1994), Exact learning of discretized concepts, Technical Report, WUCS-94-19, Washington University.
15. Chen, Z. (July 1993), Learning unions of two rectangles in the plane with equivalence queries, in "Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory," pp. 243-252, ACM Press.
16. Chen, Z., and Homer, S. (May 1994), The bounded injury priority method and the learnability of unions of rectangles, unpublished manuscript.
17. Chen, Z., and Maass, W. (July 1992), On-line learning of rectangles, in "Proceedings of the Fifth Annual Workshop on Computational Learning Theory," pp. 16-27, ACM Press.
18. Decatur, S. E. (1993), Statistical queries and faulty PAC oracles, in "Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory," pp. 262-268, ACM Press, New York, NY.
19. Edelsbrunner, H. (1987), "Algorithms in Combinatorial Geometry," Springer-Verlag, New York.
20. Ehrenfeucht, A., Haussler, D., Kearns, M., and Valiant, L. (1989), A general lower bound on the number of examples needed for learning, Inform. and Comput. 82(3), 247-251.
21. Frazier, M., Goldman, S., Mishra, N., and Pitt, L. (July 1994), Learning from a consistently ignorant teacher, in "Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory."
22. Freund, Y. (August 1990), Boosting a weak learning algorithm by majority, in "Proceedings of the Third Annual Workshop on Computational Learning Theory," pp. 202-216, Morgan Kaufmann.
23. Freund, Y. (July 1992), An improved boosting algorithm and its implications on learning complexity, in "Proceedings of the Fifth Annual Workshop on Computational Learning Theory," pp. 391-398.
24. Goldberg, P. W., Goldman, S. A., and Mathias, H. D. (July 1994), Learning unions of boxes with membership and equivalence queries, in "Proceedings of the Seventh Annual ACM Conferenc on Computational Learning Theory."
25. Haussler, D. (Oct. 1989), Generalizing the PAC model: sample size bounds from metric dimension-based uniform convergence results, in "30th Annual Symposium on Foundations of Computer Science," pp. 40-45.
26. Haussler, D., Kearns, M., Littleston, N., and Warmuth, M. K. (1991), Equivalence of models for polynomial learnability, Inform. and Comput. 25(2), 129-161.
27. Homer, S., and Chen, Z. (July 1993), Fast learning unions of rectangles with queries, unpublished manuscript.
28. Kearns, M. (1993), Efficient noise-tolerant learning from statistical queries, in "Proc. 25th Annu. ACM Sympos. Theory Comput.," pp. 392-401, ACM Press, New York, NY.
29. Littlestone, N. (1988), Learning when irrelevant attirbutes abound: a new linear-threshold algorithm, Mach. Learning 2, 285-318.
30. Long, P. M., and Warmuth, M. K. (August 1990), Composite geometric concepts and polynomial predictability, in "Proceedings of the Third Annual Workshop on Computational Learning Theory," pp. 273-287, Morgan Kaufmann.
31. Maass, W., and Turàn, G. (Oct. 1989), On the complexity of learning from counterexamples, in "30rd Annual Symposium on Foundations of Computer Science," pp. 262-267.
32. Maass, W., and Turán, G. (Oct. 1990), On the complexity of learning from counterexamples and membership queries, in "31st Annual Symposium on Foundations of Computer Science,́ pp. 203-210.
33. Maass, W., and Turán, G. (Oct. 1991), "Algorithms and lower Bounds for On-Line Learning of Geometrical Concepts," Technical IIG-Report, 316, Technische Universität Graz, TU Graz, Austria.
34. Maass, W., and Turán, G. (1992), Lower bound methods and separation results for on-line learning models, Mach. Learning 9, 107-145.
35. Schapire, R. E. (1990), The strength of weak learnability, Mach. Learning 5(2), 197-227.
36. Sloan, R. H. (1988), Types of noise in data for concept learning, in "Proceedings of the 1988 Workshop on Computational Learning Theory," pp. 91-96, Morgan Kaufmann.
37. Valiant, L. (Nov. 1984), A theory of the learnable, Comm. ACM 27(11), 1134-1142.
38. Valiant, L. (1985), Learning disjunctions of conjunctions, in "Proceedings of Ninth Internationa Joint Conference on Artificial Intelligence."
39. Vapnik, V. N., and Chervonenkis, A. Y. (1971), On the uniform convergence of relative frequencies of events to their probabilities, Theory Probab. Appl. XVI(2), 264-280.
40. Vitter, J. S., and Lin, J.-H. (1988), Learning in parallel, in "Proceedings of the 1988 Workshop on Computational Learning Theory," pp. 106-124, Morgan Kaufmann.
41. Vitter, J. S., and Lin, J.-H. (1992), Learning in parallel, Inform. and Comput. 179-202.