Theory and Applications of Agnostic PAC-Learning with Small Decision Trees

Proceedings of the 12th International Conference on Machine Learning, ICML 1995

Volumn , Issue , 1995, Pages 21-29

  Auer, Peter ^a   Holte, Robert C ^b   Maass, Wolfgang ^a  

^a GRAZ UNIVERSITY OF TECHNOLOGY   (Austria)

^b UNIVERSITY OF OTTAWA   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFICATION (OF INFORMATION); COMPUTATION THEORY; LEARNING ALGORITHMS; MACHINE LEARNING;

COMPUTATION TIME; CONTINUOUS ATTRIBUTE; ERROR RATE; PAC LEARNING; PERFORMANCE; PREDICTIVE POWER; REAL-WORLD DATASETS; SIMPLE++; SMALL DECISIONS; TRAINING SETS;

DECISION TREES;

EID: 85013576689     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (34)

1. [AL88] D. Angluin, P. Laird, Learning from noisy examples, Machine Learning, vol. 2, 1988,343 - 370.
2. [BB94] M. Bohanec, I. Bratko, Trading Accuracy for Simplicity in Decision Trees, Machine Learning, vol. 15, no. 3, 1994,223-250.
3. [BEHW89] A. Blumer, A. Ehrenfeucht, D. Haussier, M. K. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, JACM 36(4), 1989,929 - 965.
4. [BFOS84] L. Breiman, J. H. Friedman, R. A. Olshen, C. J. Stone, Classification and Regression Trees, Wadsworth (Belmont, 1984).
5. [BN92] W. Buntine, T. Niblett, A further comparison of splitting rules for decision-tree induction, Machine Learning, vol. 8, 1992, 75 - 82.
6. [CT92] D. Cohn, G. Tesauro, How tight are the Vapnik- Chervonenkis bounds, Neural Computation 4, 1992, 249 - 269.
7. [Dec93] S. E. Decatur, Statistical queries and faulty PAC oracles, Proc. of the 6th ACM Conference on Computational Learning Theory, 1993, 262 - 268.
8. [DGM95] D. P. Dobkin, D. Gunopulos, W. Maass, Computing the maximum bichromatic discrepancy, with applications in computer graphics and machine learning, invited paper for a special issue of the Journal of Computer and System Sciences.
9. [DL95] L. Devroye, G. Lugosi, Lower bounds in pattern recognition and learning, appears in Pattern recognition.
10. [DP93] A. Danyluk, F. Provost, Small Disjuncts in Action: Learning to Diagnose Errors in the Local Loop of the Telephone Network, Proc. 10th International Conf. Machine Learning (ML'93), Morgan Kaufmann, 1993,81 - 88.
11. [DSS93] H. Druker, R. Schapire, P. Simard, Improving performance in neural networks using a boosting algorithm, Advances in Neural Information Processing Systems, vol. 5, Morgan Kaufmann, 1993,42-49.
12. [EK91] T. Elomaa, J. Kivinen, Learning decision trees from noisy examples, Report A-1991 -3, Dept. of Computer Science, University of Helsinki (1991).
13. [Elo92] T. Elomaa, A hybrid approach to decision tree learning, Report C-1992-61, Dept. of Computer Science, University of Helsinki (1992).
14. [Elo94] T. Elomaa, In defense of C4.5: Notes on learning one-level decision trees, Proc. of the 11th Int. Conf. on Machine Learning, Morgan Kaufmann, 1994, 62 -69.
15. [Hau92] D. Haussler, Decision theoretic generalizations of the PAC-modelfor neural nets and other learning applications, Inf. and Comp., vol. 100,1992,78 - 150.
16. [HKST94] D. Haussier, M. Kearns, H. S. Seung, N. Tishby, Rigorous learning curve bounds from statistical mechanics, Proc. of the 7th Annual ACM Conference on Computational Learning Theory 1994, ACM-Press (1994), 76-87.
17. [Hol93] R. C. Holte, Very simple classification rules perform well on most commonly useddatasets, Machine Learning, vol. 11, 1993, 63 - 91.
18. [HSV93] K. U. Hoeffgen, H. U. Simon, K. S. Van Horn, Robust trainability of single neurons, preprint (1993)
19. [Kea93] M. Kearns, Efficient noise-tolerant learning from statistical queries, Proc. of the 25th ACM Symp. on the Theory of Computing, 1993,392 - 401.
20. [KL93] M. Kearns, M. Li, Learning in the presence of malicious errors, SIAM J. Comput., vol. 22, 1993, 807 - 837.
21. [KSS92] M. J. Kearns, R. E. Schapire, L. M. Sellie, Towardefficient agnostic learning, Proc. of the 5th ACM Workshop on Computational Learning Theory, 1992, 341 -352.
22. [Lub94] D. J. Lubinsky, Bivariate Splits and Consistent Split Criteria in Dichotomous Classification Trees, HDDissertation in Computer Science, Rutgers University (1994).
23. [Maa93] W. Maass, Agnostic PAC-learning of functions on analog neural nets, Advances in Neural Information Processing Systems, vol. 6, Morgan Kaufmann, 1994,311-318; journal version to appear in Neural Computation.
24. [Maa94] W. Maass, Efficient Agnostic PAC-Learning with Simple Hypotheses, Proc. of the 7th Annual ACM Conference on Computational Learning Theory, 1994, 67-75.
25. [Min89] J. Mingers, An empirical comparison of pruning methods for decision tree induction, Machine Learning, vol. 4, 1989, 227 - 243.
26. [Qui92] J. R. Quinlan, C4.5: Programs for Machine Learning, Morgan Kaufmann, 1992.
27. [SSSD90] D. B. Schwartz, V. K. Samalan, S. A. Solla, J. S. Denker, Exhaustive Learning, Neural Computation 2,1990,374-385.
28. [Tal94] M. Talagrand, Sharper bounds for Gaussian and empirical processes, Annals of Probability, vol. 22, 1994, 28-76.
29. [TLS89] N. Tishby, E. Lavin, S. A. Solla, Consistent inference of probabilities in layered networks: Predictions and generalizations, Proc. of IJCNN 1989, Vol. II, 403 - 409.
30. [Val84] L. G. Valiant, Ë theory of the learnable, Comm. of the ACM, vol. 27, 1984,1134 - 1142.
31. [Vap82] V. N. Vapnik, Estimations of Dependencies Based on Empirical Data, Springer (New York, 1982).
32. [WGT90] S. M. Weiss, R. Galen, P. V Tadepalli, Maximizing the predictive value of production rules, Art. Int., vol. 45,1990,47-71.
33. [WK90] S. M. Weiss, I. Kapouleas, An empirical comparison of pattern recognition, neural nets, and machine learning classification methods, Proc. of the 11th Int. Joint Conf. on Art. Int. 1990, Morgan Kaufmann, 781-787.
34. [WK91] S. M. Weiss, C. A. Kulikowski, Computer Systems that Learn, 1991, Morgan Kaufmann.