Skip to main content
SpringerLink
Log in

A Regularization Approach to Metrical Task Systems

  • Conference paper
Algorithmic Learning Theory (ALT 2010)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 6331))

Included in the following conference series:

Abstract

We address the problem of constructing randomized online algorithms for the Metrical Task Systems (MTS) problem on a metric δ against an oblivious adversary. Restricting our attention to the class of “work-based” algorithms, we provide a framework for designing algorithms that uses the technique of regularization. For the case when δ is a uniform metric, we exhibit two algorithms that arise from this framework, and we prove a bound on the competitive ratio of each. We show that the second of these algorithms is ln n + O(loglogn) competitive, which is the current state-of-the art for the uniform MTS problem.

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 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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. Borodin, A., Linial, N., Saks, M.: An optimal on-line algorithm for metrical task system. JACM: Journal of the ACM 39(4), 745–763 (1992)

    Article  MATH  MathSciNet  Google Scholar 

  2. Manasse, M., McGeoch, L., Sleator, D.: Competitive algorithms for server problems. J. Algorithms 11(2), 208–230 (1990)

    Article  MATH  MathSciNet  Google Scholar 

  3. Freund, S.: A decision-theoretic generalization of on-line learning and an application to boosting. JCSS: Journal of Computer and System Sciences 55 (1997)

    Google Scholar 

  4. Schafer, G., Sivadasan, N.: Topology matters: Smoothed competitiveness of metrical task systems. TCS: Theoretical Computer Science 341 (2005)

    Google Scholar 

  5. Irani, S., Seiden, S.: Randomized algorithms for metrical task systems. Theoretical Computer Science 194 (1998)

    Google Scholar 

  6. Bartal, Y., Blum, A., Burch, C., Tomkins, A.: A polylog( n )-competitive algorithm for metrical task systems. In: Symposium on Theory Of Computing (STOC), pp. 711–719 (1997)

    Google Scholar 

  7. Bartal, Y.: On approximating arbitrary metrics by tree metrics. In: Symposium Theory Of Computing (STOC), pp. 161–168 (1998)

    Google Scholar 

  8. Fakcharoenphol, J., Rao, S., Talwar, K.: A tight bound on approximating arbitrary metrics by tree metrics. In: Proceedings of the Thirty-Fifth Annual ACM Symposium on Theory of computing (STOC), pp. 448–455 (2003)

    Google Scholar 

  9. Fiat, A., Mendel, M.: Better algorithms for unfair metrical task systems and applications. SIAM Journal on Computing 32 (2003)

    Google Scholar 

  10. Bansal, N., Buchbinder, N., Naor, S.: Metrical task systems and the k-server problem on hsts (2009) (manuscript)

    Google Scholar 

  11. Bartal, Y., Bollobás, B., Mendel, M.: A ramsey-type theorem for metric spaces and its applications for metrical task systems and related problems. In: IEEE Symposium on Foundations of Computer Science (FOCS), pp. 396–405 (2001)

    Google Scholar 

  12. Blum, A., Karloff, H., Rabani, Y., Saks, M.: A decomposition theorem and lower bounds for randomized server problems. SIAM Journal on Computing 30, 1624–1661 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  13. Bansal, N., Buchbinder, N., Naor, J.: A primal-dual randomized algorithm for weighted paging. In: IEEE Symposium on Foundations of Computer Science, FOCS (2007)

    Google Scholar 

  14. Bein, W., Larmore, L., Noga, J.: Uniform metrical task systems with a limited number of states. IPL: Information Processing Letters 104 (2007)

    Google Scholar 

  15. Bansal, N., Buchbinder, N., Naor, S.: Towards the randomized k-server conjecture: A primal-dual approach. In: ACM-SIAM Symposium on Discrete Algorithms, SODA (2010)

    Google Scholar 

  16. Buchbinder, N., Naor, S.: The design of competitive online algorithms via a primal-dual approach. Foundations and Trends in Theoretical Computer Science 3(2-3), 93–263 (2009)

    MathSciNet  Google Scholar 

  17. Blum, A., Burch, C.: On-line learning and the metrical task system problem. Machine Learning 39(1), 35–58 (2000)

    Article  MATH  Google Scholar 

  18. Herbster, M., Warmuth, M.K.: Tracking the best expert. Machine Learning 32, 151 (1998)

    Article  MATH  Google Scholar 

  19. Kivinen, J., Warmuth, M.: Exponentiated gradient versus gradient descent for linear predictors. Information and Computation (1997)

    Google Scholar 

  20. Gordon, G.: Regret bounds for prediction problems. In: Proceedings of the Twelfth Annual Conference on Computational Learning Theory, pp. 29–40. ACM, New York (1999)

    Chapter  Google Scholar 

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

    Book  MATH  Google Scholar 

  22. Rakhlin, A.: Lecture Notes on Online Learning DRAFT (2009)

    Google Scholar 

  23. Guiau, S.: Weighted entropy. Reports on Mathematical Physics 2(3), 165–179 (1971)

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. UC Berkeley,  

    Jacob Abernethy, Peter L. Bartlett & Isabelle Stanton

  2. Microsoft Research,  

    Niv Buchbinder

Authors
  1. Jacob Abernethy
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Peter L. Bartlett
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Niv Buchbinder
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Isabelle Stanton
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Research School of Information Sciences and Engineering, Australian National University and NICTA, 0200, Canberra, ACT, Australia

    Marcus Hutter

  2. Department of Mathematics, National University of Singapore, Block S17, 10 Lower Kent Ridge Road, 119076, Singapore, Republic of Singapore

    Frank Stephan

  3. Department of Computer Science, University of London, Royal Holloway, TW20 0EX, Egham, Surrey, UK

    Vladimir Vovk

  4. Division of Computer Science, Hokkaido University, , ,, N-14, W-9, Sapporo, 060-0814, Japan

    Thomas Zeugmann

Rights and permissions

Reprints and permissions

Copyright information

© 2010 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Abernethy, J., Bartlett, P.L., Buchbinder, N., Stanton, I. (2010). A Regularization Approach to Metrical Task Systems. In: Hutter, M., Stephan, F., Vovk, V., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2010. Lecture Notes in Computer Science(), vol 6331. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16108-7_23

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-16108-7_23

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-16107-0

  • Online ISBN: 978-3-642-16108-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation