Online Variance Minimization

  • Manfred K. Warmuth
  • Dima Kuzmin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4005)


We design algorithms for two online variance minimization problems. Specifically, in every trial t our algorithms get a covariance matrix \({\mathcal{C}}_t\) and try to select a parameter vector w t such that the total variance over a sequence of trials \(\sum_t {\boldsymbol{w}}_t^{\top}{\mathcal{C}}_t{\boldsymbol{w}}_t\) is not much larger than the total variance of the best parameter vector u chosen in hindsight. Two parameter spaces are considered – the probability simplex and the unit sphere. The first space is associated with the problem of minimizing risk in stock portfolios and the second space leads to an online calculation of the eigenvector with minimum eigenvalue. For the first parameter space we apply the Exponentiated Gradient algorithm which is motivated with a relative entropy. In the second case the algorithm maintains a mixture of unit vectors which is represented as a density matrix. The motivating divergence for density matrices is the quantum version of the relative entropy and the resulting algorithm is a special case of the Matrix Exponentiated Gradient algorithm. In each case we prove bounds on the additional total variance incurred by the online algorithm over the best offline parameter.


Density Matrix Density Matrice Relative Entropy Probability Vector Online Algorithm 
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. [BV04]
    Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2004)MATHGoogle Scholar
  2. [BW02]
    Bousquet, O., Warmuth, M.K.: Tracking a small set of experts by mixing past posteriors. J. of Machine Learning Research 3, 363–396 (2002)CrossRefMathSciNetGoogle Scholar
  3. [CBMS05]
    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
  4. [Cov91]
    Cover, T.M.: Universal portfolios. Mathematical Finance 1(1), 1–29 (1991)CrossRefMathSciNetMATHGoogle Scholar
  5. [FS97]
    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)CrossRefMathSciNetMATHGoogle Scholar
  6. [CSTK01]
    Cristianini, N., Shawe-Taylor, J., Kandola, J.: Spectral kernel methods for clustering. In: Advances in Neural Information Processing Systems 14, pp. 649–655. MIT Press, Cambridge (2001)Google Scholar
  7. [HSSW98]
    Helmbold, D., Schapire, R.E., Singer, Y., Warmuth, M.K.: On-line portfolio selection using multiplicative updates. Mathematical Finance 8(4), 325–347 (1998)CrossRefMATHGoogle Scholar
  8. [HW98]
    Herbster, M., Warmuth, M.K.: Tracking the best expert. Journal of Machine Learning 32(2), 151–178 (1998)CrossRefMATHGoogle Scholar
  9. [KW97]
    Kivinen, J., Warmuth, M.K.: Additive versus exponentiated gradient updates for linear prediction. Information and Computation 132(1), 1–64 (1997)CrossRefMathSciNetMATHGoogle Scholar
  10. [LW94]
    Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108(2), 212–261 (1994)CrossRefMathSciNetMATHGoogle Scholar
  11. [NC00]
    Nielsen, M.A., Chuang, I.L.: Quantum Computation and Quantum Information. Cambridge University Press, Cambridge (2000)MATHGoogle Scholar
  12. [TRW05]
    Tsuda, K., Rätsch, G., Warmuth, M.K.: Matrix exponentiated gradient updates for on-line learning and Bregman projections. Journal of Machine Learning Research 6, 995–1018 (2005)Google Scholar
  13. [War05]
    Warmuth, M.K.: Bayes rule for density matrices. In: Advances in Neural Information Processing Systems 18 (NIPS 2005), December 2005, MIT Press, Cambridge (2005)Google Scholar
  14. [WK06]
    Warmuth, M.K., Kuzmin, D.: A Bayesian probability calculus for density matrices (March 2006) (unpublished manuscript)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Manfred K. Warmuth
    • 1
  • Dima Kuzmin
    • 1
  1. 1.Computer Science DepartmentUniversity of CaliforniaSanta Cruz

Personalised recommendations