Efficient Learning of Typical Finite Automata from Random Walks

Information and Computation

Volumn 138, Issue 1, 1997, Pages 23-48

  Freund, Yoav ^a   Kearns, Michael ^a   Ron, Dana ^b   Rubinfeld, Ronitt ^c   Schapire, Robert E ^a   Sellie, Linda ^d  

^a AT AND T LABS RESEARCH   (United States)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^c Department of Obstetrics Gynecology   (United States)

^d UNIVERSITY OF CHICAGO   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0002023197     PISSN: 08905401     EISSN: None     Source Type: Journal    
DOI: 10.1006/inco.1997.2648     Document Type: Article

References (28)

1. Angluin, D. (1987), Learning regular sets from queries and counterexamples, Inform. and Comput. 75, 87-106.
2. Angluin, Dana (1978), On the complexity of minimum inference of regular sets, Inform. and Control 39, 337-350.
3. Azar, Y., Broder, A. Z., Karlin, A. R., Linial, N., and Phillips, S. (1992), Biased random walks, in "Proceedings of the Twenty-Fourth Annual ACM Symposium on the Theory of Computing," pp. 1-9.
4. Barzdin', Y. M. (1970), Deciphering of sequential networks in the absence of an upper limit on the number of states, Sov. Phys. Dokl. 15(2), 94-97.
5. Blum, A. (1994), Some tools for approximate 3-coloring, J. Assoc. Comput. Mach. 41(3), 470-516.
6. Chor, B., and Goldreich, O. (1988), Unbiased bits from sources of weak randomness and probabilistic communication complexity, SIAM J. Comput. 17, 230-261.
7. Dean, T., Angluin, D., Basye, K., Engelson, S., Kaelbling, L., Kokkevis, E., and Maron, O. (1995), Inferring finite automata with stochastic output functions and an application to map learning, Mach. Learning 18(1), 81-108.
8. Feder, M., Merhav, N., and Gutman, M. (1992), Universal prediction of individual sequences, IEEE Trans. Inform. Theory 38, 1258-1270.
9. Feller, W. (1968), "An Introduction to Probability and Its Applications," 3rd ed., Vol. 1, Wiley, New York.
10. Gold, M. E. (1972), System identification via state characterization, Automat. 8, 621-636.
11. Gold, M. E. (1978), Complexity of automaton identification from given data, Inform. and Control 37, 302-320.
12. Haussler, D., Littlestone, N., and Warmuth, M. K. (1994), Predicting {0, 1}-functions on randomly drawn points, Inform. and Comput. 115, 248-292.
13. Kearns, M. J., Mansour, Y., Ron, D., Rubinfeld, R., Schapire, R. E., and Sellie, L. (1994), On the learnability of discrete distributions, in "The 25th Annual ACM Symposium on Theory of Computing," pp. 273-282.
14. Kearns, M. J., and Valiant, L. G. (1994), Cryptographic limitations on learning Boolean formulae and finite automata, J. Assoc. Comput. Mach. 41, 67-95.
15. Lang, K. J. (1992), Random DFA's can be approximately learned from sparse uniform examples, in "Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory," pp. 45-52.
16. Littlestone, N. (1988), Learning when irrelevant attributes abound: A new linear-threshold algorithm, Mach. Learning 2, 285-318.
17. Pitt, L., and Valiant, L. G. (1988), Computational limitations on learning from examples, J. Assoc. Comput. Mach. 35(4), 965-984.
18. Pitt, L., and Warmuth, M. K. (1990), Prediction-preserving reducibility, J. Comput. System Sci. 41(3), 430-467.
19. Pitt, L., and Warmuth, M. K. (1993), The minimum consistent DFA problem cannot be approximated within any polynomial, J. Assoc. Comput. Mach. 40(1), 95-142.
20. Rivest, R. L., and Schapire, R. E. (1993), Inference of finite automata using homing sequences, Inform. and Comput. 103(2), 299-347.
21. Rivest, R. L., and Schapire, R. E. (1994), Diversity-based inference of finite automata, J. Assoc. Comput. Mach. 43(3), 555-589.
22. Rivest, R. L., and Sloan, R. (1988), Learning complicated concepts reliably and usefully, in "Proceedings AAAI-99," pp. 635-639.
23. Ron, D., Singer, Y., and Tishby, N. (1995), On the learnability and usage of acyclic probabilistic finite automata, in "Proceedings of the Eighth Annual ACM Workshop on Computational Learning Theory," pp. 31-40.
24. Santha, M., and Vazirani, U. V. (1986), Generating quasi-random sequences from semi-random sources, J. Comput. System Sci. 33(1), 75-87.
25. Trakhtenbrot, B. A., and Barzdin', Ya. M. (1973), "Finite Automata: Behavior and Synthesis," North-Holland, Amsterdam.
26. Valiant, L. G. (1984), A theory of the learnable, Comm. ACM 27(11), 1134-1142.
27. Vazirani, U. V. (1987), Strong communication complexity or generating quasi-random sequences from two communicating semi-random sources, Combinatorica 7, 375-392.
28. Vazirani, U. V., and Vazirani, V. V. (1985), Random polynomial time is equal to slightly-random polynomial time, in "26th Annual Symposium on Foundations of Computer Science," pp. 417-428.