Abstract
We start from a simple asymptotic result for the problem of on-line regression with the quadratic loss function: the class of continuous limited-memory prediction strategies admits a “leading prediction strategy”, which not only asymptotically performs at least as well as any continuous limited-memory strategy but also satisfies the property that the excess loss of any continuous limited-memory strategy is determined by how closely it imitates the leading strategy. More specifically, for any class of prediction strategies constituting a reproducing kernel Hilbert space we construct a leading strategy, in the sense that the loss of any prediction strategy whose norm is not too large is determined by how closely it imitates the leading strategy. This result is extended to the loss functions given by Bregman divergences and by strictly proper scoring rules.
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
Adams, R.A., Fournier, J.J.F.: Sobolev Spaces, 2nd edn. Pure and Applied Mathematics, vol. 140. Academic Press, Amsterdam (2003)
Auer, P., Cesa-Bianchi, N., Gentile, C.: Adaptive and self-confident 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 43, 211–246 (2001)
Blackwell, D., Dubins, L.: Merging of opinions with increasing information. Annals of Mathematical Statistics 33, 882–886 (1962)
Bregman, L.M.: The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming. USSR Computational Mathematics and Physics 7, 200–217 (1967)
Cesa-Bianchi, N., Long, P.M., Warmuth, M.K.: Worst-case 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)
Cox, D.R., Hinkley, D.V.: Theoretical Statistics. Chapman and Hall, London (1974)
Dawid, A.P.: Statistical theory: the prequential approach. Journal of the Royal Statistical Society A 147, 278–292 (1984)
Dawid, A.P.: Calibration-based empirical probability (with discussion). Annals of Statistics 13, 1251–1285 (1985)
Dawid, A.P.: Proper measures of discrepancy, uncertainty and dependence, with applications to predictive experimental design. Technical Report 139, Department of Statistical Science, University College London, November 1994. This technical report was revised (and its title was slightly changed) in August 1998
Dawid, A.P.: Probability, causality and the empirical world: a Bayes–de Finetti–Popper–Borel synthesis. Statistical Science 19, 44–57 (2004)
Ellul, J.: The Technological Bluff. Eerdmans, Grand Rapids, MI (1990), Translated by Bromiley, G.W.: The French original: Le bluff technologique, Hachette, Paris, 1988
Helmbold, D.P., Kivinen, J., Warmuth, M.K.: Relative loss bounds for single neurons. IEEE Transactions on Neural Networks 10, 1291–1304 (1999)
Herbster, M., Warmuth, M.K.: Tracking the best linear predictor. Journal of Machine Learning Research 1, 281–309 (2001)
Kabanov, Y.M., Liptser, R.S., Shiryaev, A.N.: To the question of absolute continuity and singularity of probability measures. Matematicheskii Sbornik 104, 227–247 (1977) (in Russian)
Kivinen, J., Warmuth, M.K.: Relative loss bounds for multidimensional regression problems. Machine Learning 45, 301–329 (2001)
Levin, L.A.: On the notion of a random sequence. Soviet Mathematics Doklady 14, 1413–1416 (1973)
Martin-Löf, P.: The definition of random sequences. Information and Control 9, 602–619 (1966)
Schnorr, C.P.: Zufälligkeit und Wahrscheinlichkeit. Springer, Berlin (1971)
Shafer, G., Vovk, V.: Probability and Finance: It’s Only a Game!. Wiley, New York (2001)
Solomonoff, R.J.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Transactions on Information Theory IT-24, 422–432 (1978)
Ville, J.: Etude critique de la notion de collectif. In: Gauthier-Villars, Paris (1939)
Vovk, V.: On a randomness criterion. Soviet Mathematics Doklady 35, 656–660 (1987)
Vovk, V.: Probability theory for the Brier game. Theoretical Computer Science, 1997 261, 57–79 (2001); Conference version in: Li, M. (ed.) ALT 1997. LNCS, vol. 1316, pp. 57–79. Springer, Heidelberg (1997)
Vovk, V.: Defensive prediction with expert advice. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS (LNAI), vol. 3734, pp. 444–458. Springer, Heidelberg (2005); Full version: Technical Report arXiv:cs.LG/0506041 “Competitive on-line learning with a convex loss function” (version 3), arXiv.org e-Print archive (September 2005)
Vovk, V.: Non-asymptotic calibration and resolution. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS (LNAI), vol. 3734, pp. 429–443. Springer, Heidelberg (2005); A version of this paper can be downloaded from the arXiv.org e-Print archive (arXiv:cs.LG/0506004)
Vovk, V.: Competing with Markov prediction strategies. Technical report, arXiv.org e-Print archive (July 2006)
Vovk, V.: Competing with stationary prediction strategies. Technical Report arXiv:cs.LG/0607067, arXiv.org e-Print archive (July 2006)
Vovk, V.: Competing with wild prediction rules. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS (LNAI), vol. 4005, pp. 559–573. Springer, Heidelberg (2006); Full version: Technical Report arXiv:cs.LG/0512059 (version 2), arXiv.org e-Print archive (January 2006)
Vovk, V.: Leading strategies in competitive on-line prediction. Technical Report arXiv:cs.LG/0607134, arXiv.org e-Print archive (July 2006)
Vovk, V.: On-line regression competitive with reproducing kernel Hilbert spaces. Technical Report arXiv:cs.LG/00511058 (version 2), arXiv.org e-Print archive (January 2006); Cai, J.-Y., Cooper, S.B., Li, A. (eds.) TAMC 2006. LNCS, vol. 3959, pp. 452–463. Springer, Heidelberg (extended abstract, 2006)
Vovk, V.: Predictions as statements and decisions. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS (LNAI), vol. 4005, p. 4. Springer, Heidelberg (2006); Full version: Technical Report arXiv:cs.LG/0606093, arXiv.org e-Print archive (June 2006)
Vovk, V., Takemura, A., Shafer, G.: Defensive forecasting. In: Cowell, R.G., Ghahramani, Z. (eds.) Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics. Society for Artificial Intelligence and Statistics, pp. 365–372 (2005), Available electronically at: http://www.gatsby.ucl.ac.uk/aistats/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vovk, V. (2006). Leading Strategies in Competitive On-Line Prediction. In: Balcázar, J.L., Long, P.M., Stephan, F. (eds) Algorithmic Learning Theory. ALT 2006. Lecture Notes in Computer Science(), vol 4264. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11894841_19
Download citation
DOI: https://doi.org/10.1007/11894841_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46649-9
Online ISBN: 978-3-540-46650-5
eBook Packages: Computer ScienceComputer Science (R0)