Skip to main content
SpringerLink
Log in

Online Allocation with Risk Information

  • Conference paper
Algorithmic Learning Theory (ALT 2005)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3734))

Included in the following conference series:

Abstract

We consider the problem of dynamically apportioning resources among a set of options in a worst-case online framework. The model we investigate is a generalization of the well studied online learning model. In particular, we allow the learner to see as additional information how high the risk of each option is. This assumption is natural in many applications like horse-race betting, where gamblers know odds for all options before placing bets. We apply the Aggregating Algorithm to this problem and give a tight performance bound. The results support our intuition that we should bet more on low-risk options. Surprisingly, however, the Hedge Algorithm without seeing risk information performs nearly as well as the Aggregating Algorithm. So the risk information does not help much. Moreover, the loss bound does not depend on the values of relatively small risks.

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. Cesa-Bianchi, N., Lugosi, G.: On prediction of individual sequences. Annals of Statistics 27(6), 1865–1895 (1999)

    Article  MATH  MathSciNet  Google Scholar 

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

    MATH  MathSciNet  Google Scholar 

  3. Hannan, J.: Approximation to Bayes risk in repeated play, vol. III. Princeton University Press, Princeton (1957)

    Google Scholar 

  4. Hutter, M., Poland, J.: Prediction with expert advice by following the perturbed leader for general weights. In: Ben-David, S., Case, J., Maruoka, A. (eds.) ALT 2004. LNCS (LNAI), vol. 3244, pp. 279–293. Springer, Heidelberg (2004)

    Chapter  Google Scholar 

  5. Kalai, A., Vempala, S.: Efficient algorithms for online decision problems. In: Schölkopf, B., Warmuth, M.K. (eds.) COLT/Kernel 2003. LNCS (LNAI), vol. 2777, pp. 26–40. Springer, Heidelberg (2003)

    Chapter  Google Scholar 

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

    Article  MATH  MathSciNet  Google Scholar 

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

    Article  MathSciNet  Google Scholar 

  8. Vovk, V.: A game of prediction with expert advice. JCSS 56(2), 153–173 (1998)

    MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Graduate School of Information Sciences, Tohoku University, Sendai, 980-8579, Japan

    Shigeaki Harada, Eiji Takimoto & Akira Maruoka

Authors
  1. Shigeaki Harada
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Eiji Takimoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Akira Maruoka
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. School of Computing, National University of Singapore, 117590, Singapore

    Sanjay Jain

  2. Ruhr-Universität Bochum, Germany

    Hans Ulrich Simon

  3. Department of Information and Communication Engineering, Faculty of Electro-Communications, The University of Electro-Communications, Chofugaoka 1–5–1, Chofu, 182-8585, Tokyo, Japan

    Etsuji Tomita

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Harada, S., Takimoto, E., Maruoka, A. (2005). Online Allocation with Risk Information. In: Jain, S., Simon, H.U., Tomita, E. (eds) Algorithmic Learning Theory. ALT 2005. Lecture Notes in Computer Science(), vol 3734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11564089_27

Download citation

  • DOI: https://doi.org/10.1007/11564089_27

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-29242-5

  • Online ISBN: 978-3-540-31696-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation