Risk-Sensitive Online Learning

  • Eyal Even-Dar
  • Michael Kearns
  • Jennifer Wortman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4264)


We consider the problem of online learning in settings in which we want to compete not simply with the rewards of the best expert or stock, but with the best trade-off between rewards and risk. Motivated by finance applications, we consider two common measures balancing returns and risk: the Sharpe ratio [9] and the mean-variance criterion of Markowitz [8]. We first provide negative results establishing the impossibility of no-regret algorithms under these measures, thus providing a stark contrast with the returns-only setting. We then show that the recent algorithm of Cesa-Bianchi et al. [5] achieves nontrivial performance under a modified bicriteria risk-return measure, and give a modified best expert algorithm that achieves no regret for a “localized” version of the mean-variance criterion. We perform experimental comparisons of traditional online algorithms and the new risk-sensitive algorithms on a recent six-year S&P 500 data set and find that the modified best expert algorithm outperforms the traditional with respect to Sharpe ratio, MV, and accumulated wealth. To our knowledge this paper initiates the investigation of explicit risk considerations in the standard models of worst-case online learning.


Competitive Ratio Online Algorithm Sharpe Ratio Average Reward Good Expert 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agarwal, A., Hazan, E., Kale, S., Schapire, R.E.: Algorithms for Portfolio Management based on the Newton Method. In: ICML (2006)Google Scholar
  2. 2.
    Bodie, Z., Kane, A., Marcus, A.J.: Portfolio Performance Evaluation, 4th edn. Investments. Irwin McGraw-Hill, New York (1999)Google Scholar
  3. 3.
    Borodin, A., El-Yaniv, R., Gogan, V.: Can We Learn to Beat the Best Stock. JAIR 21, 579–594 (2004)MATHMathSciNetGoogle Scholar
  4. 4.
    Cesa-Bianchi, N., Freund, Y., Haussler, D., Helmbold, D., Schapire, R.E., Warmuth, M.K.: How to Use Expert Advice. J. of the ACM 44(3), 427–485 (1997)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Cesa-Bianchi, N., Mansour, Y., Stoltz, G.: Improved Second-Order Bounds for Prediction with Expert Advice. In: Auer, P., Meir, R. (eds.) COLT 2005. LNCS, vol. 3559, pp. 217–232. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  6. 6.
    Helmbold, D.P., Schapire, R.E., Singer, Y., Warmuth, M.K.: On-line portfolio selection using multiplicative updates. Mathematical Finance 8(4), 325–347 (1998)MATHCrossRefGoogle Scholar
  7. 7.
    Littlestone, N., Warmuth, M.K.: The Weighted Majority Algorithm. Information and Computation 108(2), 212–261 (1994)MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Markowitz, H.: Portfolio Selection. The Journal of Finance 7(1), 77–91 (1952)CrossRefGoogle Scholar
  9. 9.
    Sharpe, W.F.: Mutual Fund Performance. The Journal of Business, part 2: Supplement on Security Prices 39(1), 119–138 (1966)CrossRefGoogle Scholar
  10. 10.
    Warmuth, M.K., Kuzmin, D.: Online Variance Minimization. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS, vol. 4005, pp. 514–528. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Eyal Even-Dar
    • 1
  • Michael Kearns
    • 1
  • Jennifer Wortman
    • 1
  1. 1.Department of Computer and Information ScienceUniversity of PennsylvaniaPhiladelphiaUSA

Personalised recommendations