Learning DNF from random walks

Journal of Computer and System Sciences

Volumn 71, Issue 3, 2005, Pages 250-265

  Bshouty, Nader H ^a   Mossel, Elchanan ^b   O'Donnell, Ryan ^c   Servedio, Rocco A ^d  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^b UNIVERSITY OF CALIFORNIA   (United States)

^c INSTITUTE FOR ADVANCED STUDY   (United States)

^d Mailcode 0401 ^*  (United States)

Author keywords

Computational learning theory; Disjunctive Normal Form formulas; DNF; Noise sensitivity; Random walks

Indexed keywords

ALGORITHMS; DECISION THEORY; FUNCTIONS; MATHEMATICAL MODELS; POLYNOMIALS; TREES (MATHEMATICS);

COMPUTATIONAL LEARNING THEORY; DISJUNCTIVE NORMAL FORM FORMULAS; DNF; NOISE SENSITIVITY; RANDOM WALKS;

RANDOM PROCESSES;

EID: 24644509298     PISSN: 00220000     EISSN: 10902724     Source Type: Journal    
DOI: 10.1016/j.jcss.2004.10.010     Document Type: Conference Paper

References (38)

1. D. Aldous, U. Vazirani, A Markovian extension of Valiant's learning model, in: Proceedings of the 31st Symposium on Foundations of Computer Science, 1990, pp. 392-396.
2. P. Bartlett, P. Fischer, K.U. Höffgen, Exploiting random walks for learning, in: Proceedings of the Seventh Annual Conference on Computational Learning Theory, 1994, pp. 318-327.
3. M. Bellare, A technique for upper bounding the spectral norm with applications to learning, in: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 1992, pp. 62-70.
4. I. Benjamini, G. Kalai, and O. Schramm Noise sensitivity of boolean functions and applications to percolation Inst. Hautes Études Sci. Publ. Math. 90 1999 5 43
5. A. Blum, M. Furst, J. Jackson, M. Kearns, Y. Mansour, S. Rudich, Weakly learning DNF and characterizing statistical query learning using Fourier analysis, in: Proceedings of the 26th Annual Symposium on Theory of Computing, 1994, pp. 253-262.
6. D. Boneh, R. Lipton, Amplification of weak learning over the uniform distribution, in: Proceedings of the Sixth Annual Workshop on Computational Learning Theory, 1993, pp. 347-351.
7. N. Bshouty Exact learning via the monotone theory Inform. Comput. 123 1 1995 146 153
8. N. Bshouty, and V. Feldman On using extended statistical queries to avoid membership queries J. Mach. Learning Res. 2 2002 359 395
9. N. Bshouty, and J. Jackson Learning DNF over the uniform distribution using a quantum example oracle SIAM J. Comput. 28 3 1999 1136 1153
10. N. Bshouty, J. Jackson, C. Tamon, More efficient PAC learning of DNF with membership queries under the uniform distribution, in: Proceedings of the 12th Annual Conference on Computational Learning Theory, 1999, pp. 286-295.
11. N. Bshouty, J. Jackson, and C. Tamon Uniform-distribution attribute noise learnability Inform. Comput. 187 2 2003 277 290
12. N. Bshouty, and C. Tamon On the Fourier spectrum of monotone functions J. Assoc. Comput. Mach. 43 4 1996 747 770
13. A. Ehrenfeucht, and D. Haussler Learning decision trees from random examples Inform. Comput. 82 3 1989 231 246
14. Y. Freund, Boosting a weak learning algorithm by majority, in: Proceedings of the Third Annual Workshop on Computational Learning Theory, 1990, pp. 202-216.
15. D. Gamarnik, Extension of the PAC framework to finite and countable Markov chains, in: Proceedings of the 12th Annual Conference on Computational Learning Theory, 1999, pp. 308-317.
16. O. Goldreich, L. Levin, A hard-core predicate for all one-way functions, in: Proceedings of the 21st Annual Symposium on Theory of Computing, 1989, pp. 25-32.
17. T. Hancock, The complexity of learning formulas and decision trees that have restricted reads, Ph.D. thesis, Harvard University, 1992.
18. T. Hancock, Y. Mansour, Learning monotone k - μ DNF formulas on product distributions, in: Proceedings of the Fourth Annual Conference on Computational Learning Theory, 1991, pp. 179-193.
19. J. Hastad, R. Impagliazzo, L. Levin, and M. Luby A pseudorandom generator from any one-way function SIAM J. Comput. 28 4 1999 1364 1396
20. J. Jackson An efficient membership-query algorithm for learning DNF with respect to the uniform distribution J. Comput. System Sci. 55 1997 414 440
21. J. Jackson, A. Klivans, R. Servedio, Learnability beyond AC 0, in: Proceedings of the 34th ACM Symposium on Theory of Computing, 2002.
22. M. Kearns, and U. Vazirani An Introduction to Computational Learning Theory 1994 MIT Press Cambridge, MA
23. R. Khardon On using the Fourier transform to learn disjoint DNF Inform. Process. Lett. 49 1994 219 222
24. M. Kharitonov, Cryptographic hardness of distribution-specific learning, in: Proceedings of the 25th Annual Symposium on Theory of Computing, 1993, pp. 372-381.
25. A. Kilvans, R. Servedio, Boosting and hard-core sets, in: Proceedings of the 40th Annual Symposium on Foundations of Computer Science, 1999, pp. 624-633.
26. A. Kilvans, R. Servedio, Learning DNF in time 2 o (n 1 / 3 ), in: Proceedings of the 33rd Annual Symposium on Theory of Computing, 2001, pp. 258-265.
27. M. Krause, P. Pudlak, On the computational power of depth 2 circuits with threshold and modulo gates, in: Proceedings of the 26th Annual Symposium on Theory of Computing, 1994, pp. 48-57.
28. E. Kushilevitz, and Y. Mansour Learning decision trees using the Fourier spectrum SIAM J. Comput. 22 6 1993 1331 1348
29. N. Linial, Y. Mansour, and N. Nisan Constant depth circuits Fourier transform and learnability, J. Assoc. Comput. Mach. 40 3 1993 607 620
30. Y. Mansour An O (n log log n ) learning algorithm for DNF under the uniform distribution J. Comput. System Sci. 50 1995 543 550
31. R. Motwani, and P. Raghavan Randomized Algorithms 1995 Cambridge University Press Melbourne, Australia
32. R. O'Donnell, Hardness amplification within NP, in: Proceedings of the 34th ACM Symposium on Theory of Computing, 2002.
33. Y. Sakai, and A. Maruoka Learning monotone log-term DNF formulas under the uniform distribution Theory Comput. Systems 33 2000 17 32
34. R. Servedio, On PAC learning using Winnow, Perception, and a Preceptron-like algorithm, in: Proceedings of the 12th Annual Conference on Computational Learning Theory, 1999, pp. 296-307.
35. R. Servedio, On learning monotone DNF under product distributions, in: Proceedings of the 14th Annual Conference on Computational Learning Theory, 2001, pp. 473-489.
36. L. Valiant A theory of the learnable Comm. Assoc. Comput. Mach. 27 11 1984 1134 1142
37. K. Verbeurgt, Learning DNF under the uniform distribution in quasi-polynomial time, in: Proceedings of the Third Annual Workshop on Computational Learning Theory, 1990, pp. 314-326.
38. K. Verbeurgt, Learning sub-classes of monotone DNF on the uniform distribution, in: Proceedings of the Ninth Conference on Algorithmic Learning Theory, 1998, pp. 385-399.