Separating models of learning with faulty teachers

Theoretical Computer Science

Volumn 410, Issue 19, 2009, Pages 1903-1912

  Feldman, Vitaly ^a   Shah, Shrenik ^b  

^a IBM ALMADEN RESEARCH CENTER   (United States)

^b HARVARD UNIVERSITY   (United States)

Author keywords

Exact learning; Membership query; Models of learning; PAC

Indexed keywords

AMPLIFICATION; ROBOT LEARNING;

AMPLIFICATION FUNCTIONS; COMPUTING SYSTEMS; CRYPTOGRAPHIC ASSUMPTIONS; EXACT LEARNING; FIXED POINTS; MACHINE LEARNING RESEARCHES; MACHINE-LEARNING; MEMBERSHIP QUERY; PAC; PAC LEARNING MODELS; PAC-LEARNING; POWER OF TWOS; RANDOM SUBSETS; READ-ONCE FORMULAS; SEPARATING MODELS;

TEACHING;

EID: 62749151762     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.tcs.2009.01.017     Document Type: Article

References (26)

1. Angluin D. Queries and concept learning. Machine Learning 2 (1988) 319-342
2. Angluin D., and Laird P. Learning from noisy examples. Machine Learning 2 (1988) 343-370
3. Angluin D., and Slonim D.K. Randomly fallible teachers: Learning monotone DNF with an incomplete membership oracle. Machine Learning 14 1 (1994) 7-26
4. Barg A. Complexity issues in coding theory. Electronic Colloquium on Computational Complexity (ECCC) 4 046 (1997)
5. Berlekamp E., McEliece R., and van Tilborg H. On the inherent intractability of certain coding problems. IEEE Transactions on Information Theory (1978) 24
6. A. Blum, M. Furst, M. Kearns, R.J. Lipton, Cryptographic primitives based on hard learning problems, in: Proceedings of International Cryptology Conference on Advances in Cryptology CRYPTO, 1993, pp. 278-291
7. A. Blum, A. Kalai, H. Wasserman, Noise-tolerant learning the parity problem and the statistical query model, in: Proceedings of STOC, 2000, pp. 435-440
8. Bshouty N., and Eiron N. Learning monotone DNF from a teacher that almost does not answer membership queries. Journal of Machine Learning Research 3 (2002) 49-57
9. N.H. Bshouty, A. Owshanko, Learning regular sets with an incomplete membership oracle, in: Proceedings of COLT '01/EuroCOLT '01, 2001, pp. 574-588
10. Chen Z. A note on learning DNF formulas using equivalence and incomplete membership queries. AII '94: Proceedings of the 4th International Workshop on Analogical and Inductive Inference (1994), Springer-Verlag 272-281
11. Chernoff H. A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. The Annals of Mathematical Statistics 23 (1952) 493-507
12. Feldman V. Attribute efficient and non-adaptive learning of parities and DNF expressions. Journal of Machine Learning Research 8 (2007) 1431-1460
13. V. Feldman, P. Gopalan, S. Khot, A. Ponuswami, New results for learning noisy parities and halfspaces, in: Proceedings of FOCS, 2006, pp. 563-574
14. Goldman S., Kearns M., and Schapire R. Exact identification of read-once formulas using fixed points of amplification functions. SIAM Journal on Computing 22 4 (1993) 705-726
15. S. Goldman, H. Mathias, Learning k-term DNF formulas with an incomplete membership oracle, in: Proceedings of COLT, 1992, pp. 77-84
16. Goldreich O., Goldwasser S., and Micali S. How to construct random functions. Journal of the ACM 33 4 (1986) 792-807
17. J. Jackson, E. Shamir, C. Shwartzman, Learning with queries corrupted by classification noise, in: Proceedings of the Fifth Israel Symposium on the Theory of Computing Systems, 1997, pp. 45-53
18. Kearns M. Efficient noise-tolerant learning from statistical queries. Journal of the ACM 45 6 (1998) 983-1006
19. Kearns M., and Vazirani U. An Introduction to Computational Learning Theory (1994), MIT Press, Cambridge, MA
20. Kushilevitz E., and Mansour Y. Learning decision trees using the Fourier spectrum. SIAM Journal on Computing 22 6 (1993) 1331-1348
21. K.J. Lang, E.B. Baum, Query learning can work poorly when a human oracle is used, in: Proceedings of International Joint Conference on Neural Networks, 1992, pp. 609-614
22. R.J. McEliece, A public-key cryptosystem based on algebraic coding theory, DSN Progress Report, 1978, pp. 42-44
23. Oded Regev, On lattices, learning with errors random linear codes and cryptography, in: Proccedings of STOC, 2005, pp. 84-93
24. Simon H. How many missing answers can be tolerated by query learners?. Theory of Computing Systems 37 1 (2004) 77-94
25. Valiant L.G. A theory of the learnable. Communications of the ACM 27 11 (1984) 1134-1142
26. A. Vardy, Algorithmic complexity in coding theory and the minimum distance problem, in: Proceedings of STOC, 1997, pp. 92-109