On-Line Algorithms in Machine Learning

  • Avrim Blum
Chapter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1442)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D. Angluin. Queries and concept learning. Machine Learning, 2(4):319–342, 1988.Google Scholar
  2. 2.
    R. Armstrong, D. Freitag, T. Joachims, and T. Mitchell. Webwatcher: A learning apprentice for the world wide web. In 1995 AAAI Spring Symposium on Information Gathering from Heterogeneous Distributed Environments, March 1995.Google Scholar
  3. 3.
    P. Auer and M.K. Warmuth. Tracking the best disjunction. In Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pages 312–321, 1995.Google Scholar
  4. 4.
    D. Blackwell. An analog of the minimax theorem for vector payoffs. Pacific J. Math., 6:1–8, 1956.Google Scholar
  5. 5.
    A. Blum. Learning boolean functions in an infinite attribute space. Machine Learning, 9:373–386, 1992.Google Scholar
  6. 6.
    A. Blum. Separating distribution-free and mistake-bound learning models over the boolean domain. SIAM J. Computing, 23(5):990–1000, October 1994.CrossRefGoogle Scholar
  7. 7.
    A. Blum. Empirical support for winnow and weighted-majority based algorithms: results on a calendar scheduling domain. In Proceedings of the Twelflh International Conference on Machine Learning, pages 64–72, July 1995.Google Scholar
  8. 8.
    A. Blum and C. Burch. On-line learning and the metrical task system problem. In Proceedings of the 10th Annual Conference on Computational Learning Theory, pages 45–53, 1997.Google Scholar
  9. 9.
    A. Blum, L. Hellerstein, and N. Littlestone. Learning in the presence of finitely or infinitely many irrelevant attributes. J. Comp. Syst. Sci., 50(1):32–40, 1995.CrossRefGoogle Scholar
  10. 10.
    A. Blum and A. Kalai. Universal portfolios with and without transaction costs. In Proceedings of the 10th Annual Conference on Computational Learning Theory, pages 309–313, 1997.Google Scholar
  11. 11.
    N. Cesa-Bianchi, Y. Freund, D. P. Helmbold, and M. Warmuth. On-line prediction and conversion strategies. In Computational Learning Theory: Eurocolt '93, volume New Series Number 53 of The Institute of Mathematics and its Applications Conference Series, pages 205–216, Oxford, 1994. Oxford University Press.Google Scholar
  12. 12.
    N. Cesa-Bianchi, Y. Freund, D.P. Helmbold, D. Haussler, R.E. Schapire, and M.K. Warmuth. How to use expert advice. In Annual ACM Symposium on Theory of Computing, pages 382–391, 1993.Google Scholar
  13. 13.
    T.M. Cover. Universal portfolios. Mathematical Finance, 1(1):1–29, January 1991.Google Scholar
  14. 14.
    T.M. Cover and E. Ordentlich. Universal portfolios with side information. IEEE Transactions on Information Theory, 42(2), March 1996.Google Scholar
  15. 15.
    A. DeSantis, G. Markowsky, and M. Wegman. Learning probabilistic prediction functions. In Proceedings of the 29th IEEE Symposium on Foundations of Computer Science, pages 110–119, Oct 1988.Google Scholar
  16. 16.
    M. Feder, N. Merhav, and M. Gutman. Universal prediction of individual sequences. IEEE Transactions on Information Theory, 38:1258–1270, 1992.CrossRefGoogle Scholar
  17. 17.
    D.P. Foster and R.V. Vohra. A randomization rule for selecting forecasts. Operations Research, 41:704–709, 1993.Google Scholar
  18. 18.
    Y. Freund. Predicting a binary sequence almost as well as the optimal biased coin. In Proceedings of the 9th Annual Conference on Computational Learning Theory, pages 89–98, 1996.Google Scholar
  19. 19.
    Y. Freund and R. Schapire. Game theory, on-line prediction and boosting. In Proceedings of the 9th Annual Conference on Computational Learning Theory, pages 325–332, 1996.Google Scholar
  20. 20.
    D. Helmbold, R. Sloan, and M. K. Warmuth. Learning nested differences of intersection closed concept classes. Machine Learning, 5(2):165–196, 1990.Google Scholar
  21. 21.
    M. Kearns. Efficient noise-tolerant learning from statistical queries. In Proceedings of the Twenty-Fifth Annual ACM Symposium on Theory of Computing, pages 392–401, 1993.Google Scholar
  22. 22.
    M. Kearns, M. Li, L. Pitt, and L. Valiant. On the learnability of boolean formulae. In Proceedings of the Nineteenth Annual ACM Symposium on the Theory of Computing, pages 285–295, New York, New York, May 1987.Google Scholar
  23. 23.
    M. Kearns, R. Schapire, and L. Sellie. Toward efficient agnostic learning. Machine Learning, 17(2/3):115–142, 1994.Google Scholar
  24. 24.
    N. Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285–318, 1988.Google Scholar
  25. 25.
    N. Littlestone. personal communication (a mistake-bound version of Rivest's decision-list algorithm), 1989.Google Scholar
  26. 26.
    N. Littlestone. Redundant noisy attributes, attribute errors, and linear-threshold learning using winnow. In Proceedings of the Fourth Annual Workshop on Computational Learning Theory, pages 147–156, Santa Cruz, California, 1991. Morgan Kaufmann.Google Scholar
  27. 27.
    N. Littlestone, P. M. Long, and M. K. Warmuth. On-line learning of linear functions. In Proc. of the 23rd Symposium on Theory of Computing, pages 465–475. ACM Press, New York, NY, 1991. See also UCSC-CRL-91-29.Google Scholar
  28. 28.
    N. Littlestone and M. K. Warmuth. The weighted majority algorithm. Information and Computation, 108(2):212–261, 1994.Google Scholar
  29. 29.
    N. Merhav and M. Feder. Universal sequential learning and decisions from individual data sequences. In Proc. 5th Annual Workshop on Comput. Learning Theory, pages 413–427. ACM Press, New York, NY, 1992.Google Scholar
  30. 30.
    E. Ordentlich and T.M. Cover. On-line portfolio selection. In COLT 96, pages 310–313, 1996. A journal version is to be submitted to Mathematics of Operations Research.Google Scholar
  31. 31.
    R.L. Rivest. Learning decision lists. Machine Learning, 2(3):229–246, 1987.Google Scholar
  32. 32.
    H. Robbins. Asymptotically subminimax solutions of compound statistical decision problems. In Proc. 2nd Berkeley Symp. Math. Statist. Prob., pages 131–148, 1951.Google Scholar
  33. 33.
    J. Shtarkov. Universal sequential coding of single measures. Problems of Information Transmission, pages 175–185, 1987.Google Scholar
  34. 34.
    L.G. Valiant. A theory of the learnable. Comm. ACM, 27(11):1134–1142, November 1984.CrossRefGoogle Scholar
  35. 35.
    V. Vovk. Aggregating strategies. In Proceedings of the Third Annual Workshop on Computational Learning Theory, pages 371–383. Morgan Kaufmann, 1990.Google Scholar
  36. 36.
    V. G. Vovk. A game of prediction with expert advice. In Proceedings of the 8th Annual Conference on Computational Learning Theory, pages 51–60. ACM Press, New York, NY, 1995.Google Scholar

Copyright information

© Springer-Verlag 1998

Authors and Affiliations

  • Avrim Blum

There are no affiliations available

Personalised recommendations