Abstract
In this paper the problem of Prediction with Expert Advice is considered. We apply an existing algorithm, the Aggregating Algorithm, to a specific class of experts. This class of experts approximates (with respect to its parameter) the class of continuous functions and in this way it is close to a natural way of describing a possible dependence between two variables (continuous). We develop an explicit algorithm and prove an upper bound on the difference between the loss of our algorithm and the loss of the best expert, which has the order of the squared logarithm of the number of steps of the algorithm. This bound lies between existing bounds which have the form of the logarithm of the number of steps and the square root of the number of steps. Having more sets (algorithm, class of experts, upper bound) helps in choosing an appropriate way of solving the problem of Prediction with Expert Advice for a particular application.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Auer, P., Cesa-Bianchi, N., Gentile, C.: Adaptive and selfconfident on-line learning algorithms. Journal of Computer and System Sciences 64, 48–75 (2002)
Azoury, K.S., Warmuth, M.K.: Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions. Machine Learning, 211–246 (2001)
Cesa-Bianchi, N., Long, P.M., Warmuth, M.K.: Worstcase quadratic loss bounds for on-line prediction of linear functions by gradient descent. IEEE Transactions on Neural Networks 7, 604–619 (1996)
Cesa-Bianchi, N., Lugosi, G.: Prediction, learning, and games. Cambridge University Press, Cambridge (2006)
Freund, Y.: Predicting a binary sequence almost as well as the optimal biased coin. In: Proc. 9th Annu. Conf. on Comput. Learning Theory, pp. 89–98 (1996)
Hazan, E., Kalai, A., Kale, S., Agarwal, A.: Logarithmic Regret Algorithms for Online Convex Optimization. Machine Learning 69(2-3), 169–192 (2007)
Kolmogorov, A.N., Tikhomirov, V.M.: ε-Entropy and ε-Capacity of Sets in a Functional Space. Usp. Mat. Nauk 14(2), 3–86 (1959); Russian Mathematical Surveys 17, 277 (1961) (Translation)
Vovk, V.: On-line regression competitive with reproducing kernel Hilbert spaces (2008), http://arxiv.org/abs/cs.LG/0511058
Vovk, V.: Competitive On-line Statistics. International Statistical Review 69, 213–248 (2001)
Vovk, V.: Metric entropy in competitive on-line prediction (2006), http://arxiv.org/abs/cs.LG/0609045
Vovk, V., Nouretdinov, I., Takemura, A., Shafer, G.: Defensive forecasting for linear protocols (2005), http://arxiv.org/abs/cs.LG/0506007
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dashevskiy, M. (2008). Aggregating Algorithm for a Space of Analytic Functions. In: Freund, Y., Györfi, L., Turán, G., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2008. Lecture Notes in Computer Science(), vol 5254. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87987-9_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-87987-9_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87986-2
Online ISBN: 978-3-540-87987-9
eBook Packages: Computer ScienceComputer Science (R0)