Abstract
Consider the following setting for an on-line algorithm (introduced in [FS97]) that learns from a set of experts: In trial t the algorithm chooses an expert with probability p \(^{t}_{i}\) . At the end of the trial a loss vector L t ∈ [0,R]n for the n experts is received and an expected loss of ∑ i p \(^{t}_{i}\) L \(^{t}_{i}\) is incurred. A simple algorithm for this setting is the Hedge algorithm which uses the probabilities \(p^{t}_{i} \sim exp^{-\eta L^{<t}_{i}}\). This algorithm and its analysis is a simple reformulation of the randomized version of the Weighted Majority algorithm (WMR) [LW94] which was designed for the absolute loss. The total expected loss of the algorithm is close to the total loss of the best expert \(L_{*} = min_{i}L^{\leq T}_{i}\). That is, when the learning rate is optimally tuned based on L *, R and n, then the total expected loss of the Hedge/WMR algorithm is at most
The factor of \(\sqrt{\bf 2}\) is in some sense optimal [Vov97].
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
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)
Kalai, A., Vempala, S.: Efficient algorithms for online decision problems. J. Computer System Sci. (2005) (to appear)
Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108(2), 212–261 (1994)
Takimoto, E., Warmuth, M.K.: Path kernels and multiplicative updates. Journal of Machine Learning Research 4, 773–818 (2003)
Valiant, L.: The complexity of enumeration and reliability problems. SIAM Journal on Computing 8, 410–421 (1979)
Vovk, V.: A game of prediction with expert advice. J. Computer System Sci. (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kuzmin, D., Warmuth, M.K. (2005). Optimum Follow the Leader Algorithm. In: Auer, P., Meir, R. (eds) Learning Theory. COLT 2005. Lecture Notes in Computer Science(), vol 3559. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11503415_46
Download citation
DOI: https://doi.org/10.1007/11503415_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26556-6
Online ISBN: 978-3-540-31892-7
eBook Packages: Computer ScienceComputer Science (R0)