Abstract
Recently, it was shown that calibration with an error less than δ> 0 is almost surely guaranteed with a randomized forecasting algorithm, where forecasts are chosen using randomized rounding up to δ of deterministic forecasts. We show that this error can not be improved for a large majority of sequences generated by a probabilistic algorithm: we prove that combining outcomes of coin-tossing and a transducer algorithm, it is possible to effectively generate with probability close to one a sequence “resistant” to any randomized rounding forecasting with an error much smaller than δ.
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
Dawid, A.P.: The well-calibrated Bayesian [with discussion]. J. Am. Statist. Assoc. 77, 605–613 (1982)
Dawid, A.P.: Calibration-based empirical probability [with discussion]. Ann. Statist. 13, 1251–1285 (1985)
Dawid, A.P.: The impossibility of inductive inference. J. Am. Statist. Assoc. 80, 340–341 (1985)
Foster, D.P., Vohra, R.: Asymptotic calibration. Biometrika 85, 379–390 (1998)
Kakade, S.M., Foster, D.P.: Deterministic calibration and Nash equilibrium. In: Shawe-Taylor, J., Singer, Y. (eds.) COLT 2004. LNCS (LNAI), vol. 3120, pp. 33–48. Springer, Heidelberg (2004)
Oakes, D.: Self-calibrating priors do not exists [with discussion]. J. Am. Statist. Assoc. 80, 339–342 (1985)
Rogers, H.: Theory of recursive functions and effective computability. McGraw-Hill, New York (1967)
Vovk, Vladimir, Takemura, Akimichi, Shafer, Glenn: Defensive Forecasting. In: Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics. pp. 365–372 (2005), http://arxiv.org/abs/cs/0505083
V’yugin, V.V.: Non-stochastic infinite and finite sequences. Theor. Comp. Science. 207, 363–382 (1998)
Uspensky, V.A., Semenov, A.L., Shen, A.K.: Can an individual sequence of zeros and ones be random. Russian Math. Surveys 45(1), 121–189 (1990)
Zvonkin, A.K., Levin, L.A.: The complexity of finite objects and the algorithmic concepts of information and randomness. Russ. Math. Surv. 25, 83–124 (1970)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
V’yugin, V.V. (2007). On Calibration Error of Randomized Forecasting Algorithms. In: Hutter, M., Servedio, R.A., Takimoto, E. (eds) Algorithmic Learning Theory. ALT 2007. Lecture Notes in Computer Science(), vol 4754. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75225-7_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-75225-7_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75224-0
Online ISBN: 978-3-540-75225-7
eBook Packages: Computer ScienceComputer Science (R0)