Advertisement

Improving Confidence of Dual Averaging Stochastic Online Learning via Aggregation

  • Sangkyun Lee
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7526)

Abstract

Stochastic online learning algorithms typically exhibit slow convergence speed, but their solutions of moderate accuracy often suffice in practice. Since the outcomes of these algorithms are random variables, not only their accuracy but also their probability of achieving a certain accuracy, called confidence, is important. We show that a rather simple aggregation of outcomes from parallel dual averaging runs can provide a solution with improved confidence, and it can be controlled by the number of runs, independently of the length of learning processes.

Keywords

Empirical Risk Subgradient Method Dual Average Simple Aggregation Machine Learn Research 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hoeffding, W.: Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association 58(301), 13–30 (1963)MathSciNetzbMATHCrossRefGoogle Scholar
  2. 2.
    Lee, S., Wright, S.: Manifold identification of dual averaging methods for regularized stochastic online learning. In: Proceedings of the 28th International Conference on Machine Learning, pp. 1121–1128 (2011)Google Scholar
  3. 3.
    Nesterov, Y.: Primal-dual subgradient methods for convex problems. Mathematical Programming 120, 221–259 (2009)MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    Rockafellar, R.T., Wets, R.J.B.: On the interchange of subdifferentiation and conditional expectation for convex functionals. Stochastics 7(3), 173–182 (1982)MathSciNetzbMATHCrossRefGoogle Scholar
  5. 5.
    Xiao, L.: Dual averaging methods for regularized stochastic learning and online optimization. Journal of Machine Learning Research 11, 2543–2596 (2010)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Sangkyun Lee
    • 1
  1. 1.Fakultät für Informatik, LS VIIITechnische Universität DortmundDortmundGermany

Personalised recommendations