Computational sample complexity and attribute-efficient learning

Journal of Computer and System Sciences

Volumn 60, Issue 1, 2000, Pages 161-178

  Servedio, Rocco A ^a  

^a HARVARD UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; BOOLEAN FUNCTIONS; CODES (SYMBOLS); COMPUTATIONAL COMPLEXITY; CRYPTOGRAPHY; DECISION THEORY; ERROR CORRECTION; PROBABILITY; THEOREM PROVING;

ATTRIBUTE EFFICIENT LEARNING; LOGARITHMIC FACTOR; PSEUDORANDOM GENERATORS; SAMPLE COMPLEXITY;

LEARNING ALGORITHMS;

EID: 0034140159     PISSN: 00220000     EISSN: None     Source Type: Journal    
DOI: 10.1006/jcss.1999.1666     Document Type: Article

References (31)

1. D. Angluin and L. G. Valiant, Fast probabilistic algorithms for Hamiltonian circuits and matchings, J. Comput. System Sci. 48 (1979), 155-193.
2. A. Blum, "On-line Algorithms in Machine Learning," available at http://www.cs.edu/̃avrim/Papers/
3. pubs.html, 1996.
4. A. Blum, Empirical support for winnow and weighted-majority algorithms: results on calendar scheduling domain, Mach. Learning 26 (1997), 5-23.
5. A. Blum, L. Hellerstein, and N. Littlestone, Learning in the presence of finitely or infinitely many irrelevant attributes, J. Comput. System Sci. 50 (1995), 32-40.
6. M. Blum and S. Micali, How to generate cryptographically strong sequences of pseudo-random bits, SIAM J. Comput. 13 (1984), 850-864.
7. A. Blumer, A. Ehrenfeucht, D. Haussler, and M. K. Warmuth, Occam's razor, Inform. Process. Lett. 24 (1987), 377-380.
8. N. Bshouty and L. Hellerstein, Attribute efficient learning with queries, J. Comput. System Sci. 56 (1998), 310-319.
9. I. Dagan, Y. Karov, and D. Roth, Mistake-driven learning in text categorization, in "2nd Conf. on Empirical Methods in Natural Language Processing (EMNLP-97)," 1997.
10. S. E. Decatur, O. Goldreich, and D. Ron, Computational sample complexity, in "Proc. Tenth Ann. Conf. on Comput. Learning Theory," pp. 130-142, ACM Press, New York, 1997.
11. A. Ehrenfeucht, D. Haussler, M. Kearns, and L. Valiant, A general lower bound on the number of examples needed for learning, Inform. and Comput. 82 (1989), 247-261.
12. A. R. Golding and D. Roth, A winnow-based approach to spelling correction, Mach. Learning 34 (1999), 107-130.
13. O. Goldreich, "Foundations of Cryptography (Fragments of a Book)," available at http://www. wisdom.weizmann.ac.il/̃oded/frag.html, 1995.
14. O. Goldreich, "Modern Cryptography, Probabilistic Proofs and Pseudo-randomness," Algorithms and Combinatorics Series, Vol. 17, Springer-Verlag, Berlin/New York, 1998.
15. O. Goldreich and L. Levin, A hard-core predicate for all one-way functions, in "Proc. 21st Ann. Symp. on Theory of Comp.," pp. 25-32, ACM Press, New York, 1995.
16. S. Goldwasser and M. Bellare, "Lecture Notes on Cryptography," available at http://www.cse.ucsd. edu/users/mihir/papers/gb.html, 1996.
17. D. Haussler, Quantifying inductive bias: AI learning algorithms and Valiant's learning framework, Artificial Intelligence 36 (1988), 177-221.
18. M. Kearns, M. Li, L. Pitt, and L. Valiant, Recent results on boolean concept learning, in "Proc. 4th Int. Workshop on Machine Learning," pp. 337-352, Morgan Kaufmann, Los Altos, CA, 1987.
19. M. J. Kearns and R. E. Schapire, Efficient distribution-free learning of probabilistic concepts, J. Comput. System Sci. 48 (1994), 464-497.
20. M. Kearns and L. G. Valiant, Cryptographic limitations on learning boolean formulae and finite automata, J. Assoc. Comput. Mach. 41 (1994), 67-95.
21. M. Kearns and U. Vazirani, "An Introduction to Computational Learning Theory," MIT Press, Cambridge, MA, 1994.
22. M. Kharitonov, Cryptographic lower bounds for learnability of boolean functions on the uniform distribution, J. Comput. Systems Sci. 50 (1995), 600-610.
23. N. Littlestone, Learning quickly when irrelevant attributes abound: a new linear-threshold learning algorithm, Mach. Learning 2 (1988), 285-318.
24. N. Littlestone, "Mistake Bounds and Logarithmic Linear-Threshold Learning Algorithms," Ph.D. thesis Technical Report UCSC-CRL-89-11 Univ. of Calif., Santa Cruz, 1989.
25. M. Rabin, "Digitalized Signature as Intractable as Factorization," Technical Report MIT/LCS/TR-212 MIT Lab. for Comp. Sci., 1979.
26. R. L. Rivest, Learning decision lists, Mach. Learning 2 (1987), 229-246.
27. M. Sipser and D. A. Spielman, Expander codes, IEEE Trans. Inform. Theory 42 (1996), 1710-1722.
28. D. A. Spielman, Linear-time encodable and decodable error-correcting codes, IEEE Trans. Inform. Theory 42 (1996), 1723-1731.
29. R. Uehara, K. Tsuchida, and I. Wegener, Optimal attribute-efficient learning of disjunction, parity, and threshold functions, in "Proc. 3rd European Conf. on Comp. Learning Theory," Lecture Notes in Artificial Intelligence, pp. 1761-184, Springer-Verlag, Berlin/New York, 1997.
30. L. G. Valiant, A theory of the learnable, Comm. Assoc. Comput. Mach. 27 (1984), 1134-1142.
31. L. G. Valiant, Projection learning, in "Proc. Eleventh Ann. Conf. on Comp. Learning Theory," pp. 287-293, ACM Press, New York, 1998.