Abstract
We consider a general class of forecasting protocols, called “linear protocols”, and discuss several important special cases, including multi-class forecasting. Forecasting is formalized as a game between three players: Reality, whose role is to generate objects and their labels; Forecaster, whose goal is to predict the labels; and Skeptic, who tries to make money on any lack of agreement between Forecaster’s predictions and the actual labels. Our main mathematical result is that for any continuous strategy for Skeptic in a linear protocol there exists a strategy for Forecaster that does not allow Skeptic’s capital to grow. This result is a meta-theorem that allows one to transform any constructive law of probability in a linear protocol into a forecasting strategy whose predictions are guaranteed to satisfy this law. We apply this meta-theorem to a weak law of large numbers in inner product spaces to obtain a version of the K29 prediction algorithm for linear protocols and show that this version also satisfies the attractive properties of proper calibration and resolution under a suitable choice of its kernel parameter, with no assumptions about the way the data is generated.
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
Agarwal, R.P., Meehan, M., O’Regan, D.: Fixed Point Theory and Applications. Cambridge University Press, Cambridge (2001)
Philip Dawid, A.: Probability forecasting. In: Kotz, S., Johnson, N.L., Read, C.B. (eds.) Encyclopedia of Statistical Sciences, vol. 7, pp. 210–218. Wiley, New York (1986)
Foster, D.P., Vohra, R.V.: Asymptotic calibration. Biometrika 85, 379–390 (1998)
Gray, A.: Tubes, 2nd edn. Birkhäuser, Basel (2004)
Kolmogorov, A.N.: Sur la loi des grands nombres. Atti della Reale Accademia Nazionale dei Lincei. Classe di scienze fisiche, matematiche, e naturali. Rendiconti Serie VI 185, 917–919 (1929)
Morse, M.: Singular points of vector fields under general boundary conditions. American Journal of Mathematics 51, 165–178 (1929)
Press, W.H., Flannery, B.P., Teukolsky, S.A., Vetterling, W.T.: Numerical Recipes in C, 2nd edn. Cambridge University Press, Cambridge (1992)
Schneider, R.: Convex Bodies: The Brunn–Minkowski Theory. Cambridge University Press, Cambridge (1993)
Shafer, G., Vovk, V.: Probability and Finance: It’s Only a Game! Wiley, New York (2001)
Steinwart, I.: On the influence of the kernel on the consistency of support vector machines. Journal of Machine Learning Research 2, 67–93 (2001)
Stoltenberg-Hansen, V., Tucker, J.V.: Computable and continuous partial homomorphisms on metric partial algebras. Bulletin of Symbolic Logic 9, 299–334 (2003)
Vovk, V.: Defensive prediction with expert advice. These Proceedings
Vovk, V.: Non-asymptotic calibration and resolution. These Proceedings
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
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vovk, V., Nouretdinov, I., Takemura, A., Shafer, G. (2005). Defensive Forecasting for Linear Protocols. In: Jain, S., Simon, H.U., Tomita, E. (eds) Algorithmic Learning Theory. ALT 2005. Lecture Notes in Computer Science(), vol 3734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11564089_35
Download citation
DOI: https://doi.org/10.1007/11564089_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29242-5
Online ISBN: 978-3-540-31696-1
eBook Packages: Computer ScienceComputer Science (R0)