Skip to main content
SpringerLink
Log in

Learning Permutations with Exponential Weights

  • Conference paper
Learning Theory (COLT 2007)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 4539))

Included in the following conference series:

Abstract

We give an algorithm for learning a permutation on-line. The algorithm maintains its uncertainty about the target permutation as a doubly stochastic matrix. This matrix is updated by multiplying the current matrix entries by exponential factors. These factors destroy the doubly stochastic property of the matrix and an iterative procedure is needed to re-normalize the rows and columns. Even though the result of the normalization procedure does not have a closed form, we can still bound the additional loss of our algorithm over the loss of the best permutation chosen in hindsight.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: The nonstochastic multiarmed bandit problem. SIAM Journal on Computing 32(1), 48–77 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  2. Blum, A., Chawla, S., Kalai, A.: Static optimality and dynamic search-optimality in lists and trees. Algorithmica 36, 249–260 (2003)

    Article  MATH  MathSciNet  Google Scholar 

  3. Bhatia, R.: Matrix Analysis. Springer, Heidelberg (1997)

    Google Scholar 

  4. Balakrishnan, H., Hwang, I., Tomlin, C.: Polynomial approximation algorithms for belief matrix maintenance in identity management. In: 43rd IEEE Conference on Decision and Control, pp. 4874–4879 (December 2004)

    Google Scholar 

  5. Bousquet, O., Warmuth, M.K.: Tracking a small set of experts by mixing past posteriors. Journal of Machine Learning Research 3, 363–396 (2002)

    Article  MathSciNet  Google Scholar 

  6. Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, Cambridge (2006)

    MATH  Google Scholar 

  7. Censor, Y., Lent, A.: An iterative row-action method for interval convex programming. Journal of Optimization Theory and Applications 34(3), 321–353 (1981)

    Article  MATH  MathSciNet  Google Scholar 

  8. Franklin, J., Lorenz, J.: On the scaling of multidimensional matrices. Linear Algebra and its applications, 114/115, 717–735 (1989)

    Google Scholar 

  9. Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences 55(1), 119–139 (1997)

    Article  MATH  MathSciNet  Google Scholar 

  10. Martin Furer. Quadratic convergence for scaling of matrices. In: Proceedings of ALENEX/ANALCO, pp. 216–223. SIAM (2004)

    Google Scholar 

  11. Helmbold, D.P., Schapire, R.E.: Predicting nearly as well as the best pruning of a decision tree. Machine Learning 27(01), 51–68 (1997)

    Article  Google Scholar 

  12. Herbster, M., Warmuth, M.K.: Tracking the best linear predictor. Journal of Machine Learning Research 1, 281–309 (2001)

    Article  MATH  MathSciNet  Google Scholar 

  13. Kalai, A.: Simulating weighted majority with FPL. Private communication (2005)

    Google Scholar 

  14. Kalantari, B., Khachiyan, L.: On the complexity of nonnegative-matrix scaling. Linear Algebra and its applications 240, 87–103 (1996)

    Article  MATH  MathSciNet  Google Scholar 

  15. Kalai, A., Vempala, S.: Efficient algorithms for online decision problems (Special issue Learning Theory 2003). J. Comput. Syst. Sci. 71(3), 291–307 (2003)

    Article  MathSciNet  Google Scholar 

  16. Kivinen, J., Warmuth, M.K.: Additive versus exponentiated gradient updates for linear prediction. Information and Computation 132(1), 1–64 (1997)

    Article  MATH  MathSciNet  Google Scholar 

  17. Kivinen, J., Warmuth, M.K.: Averaging expert predictions. In: Fischer, P., Simon, H.U. (eds.) EuroCOLT 1999. LNCS (LNAI), vol. 1572, pp. 153–167. Springer, Heidelberg (1999)

    Chapter  Google Scholar 

  18. Kuzmin, D., Warmuth, M.K.: Optimum follow the leader algorithm (Open problem). In: Auer, P., Meir, R. (eds.) COLT 2005. LNCS (LNAI), vol. 3559, pp. 684–686. Springer, Heidelberg (2005)

    Google Scholar 

  19. Linial, N., Samorodnitsky, A., Wigderson, A.: A deterministic strongly polynomial algorithm for matrix scaling and approximate permanents. Combinatorica 20(4), 545–568 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  20. Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Inform. Comput. 108(2), 212–261 (1994)

    Article  MATH  MathSciNet  Google Scholar 

  21. McAllester, D.: PAC-Bayesian stochastic model selection. Machine Learning 51(1), 5–21 (2003)

    Article  MATH  Google Scholar 

  22. Sinkhorn, R.: A relationship between arbitrary positive matrices and doubly stochastic matrices. The. Annals of Mathematical Staticstics 35(2), 876–879 (1964)

    MathSciNet  Google Scholar 

  23. Takimoto, E., Warmuth, M.K.: Path kernels and multiplicative updates. Journal of Machine Learning Research 4, 773–818 (2003)

    Article  MathSciNet  Google Scholar 

  24. Warmuth, M.K., Kuzmin, D.: Randomized PCA algorithms with regret bounds that are logarithmic in the dimension. In: Advances in Neural Information Processing Systems 19 (NIPS 06), MIT Press, Cambridge (2006)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Science Department, University of California, Santa Cruz,  

    David P. Helmbold & Manfred K. Warmuth

Authors
  1. David P. Helmbold
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Manfred K. Warmuth
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Nader H. Bshouty Claudio Gentile

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer Berlin Heidelberg

About this paper

Cite this paper

Helmbold, D.P., Warmuth, M.K. (2007). Learning Permutations with Exponential Weights. In: Bshouty, N.H., Gentile, C. (eds) Learning Theory. COLT 2007. Lecture Notes in Computer Science(), vol 4539. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72927-3_34

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-72927-3_34

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-72925-9

  • Online ISBN: 978-3-540-72927-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation