Abstract
This paper is concerned with the problem of on-line prediction in the situation where some data is unlabelled and can never be used for prediction, and even when data is labelled, the labels may arrive with a delay. We construct a modification of randomised Transductive Confidence Machine for this case and prove a necessary and sufficient condition for its predictions being calibrated, in the sense that in the long run they are wrong with a prespecified probability under the assumption that data is generated independently by same distribution. The condition for calibration turns out to be very weak: feedback should be given on more than a logarithmic fraction of steps.
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
Nouretdinov, I., Melluish, T., Vovk, V.: Ridge Regression Confidence Machine. In: Proceedings of the 18th International Conference on Machine Learning (2001)
Ryabko, D., Vovk, V., Gammerman, A.: Online region prediction with real teachers (submitted for publication)
Saunders, C., Gammerman, A., Vovk, V.: Transduction with confidence and credibility. In: Proceedings of the 16th International Joint Conference on Artificial Intelligence, pp. 722–726 (1999)
Vovk, V., Gammerman, A., Saunders, C.: Machine-learning applications of algorithmic randomness. In: Proceedings of the 16th International Conference on Machine Learning, pp. 444–453. Morgan Kaufmann, San Francisco (1999)
Vovk, V.: On-line Confidence Machines are well-calibrated. In: Proceedings of the 43rd Annual Symposium on Foundations of Computer Science, IEEE Computer Society Press, Los Alamitos (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nouretdinov, I., Vovk, V. (2003). Criterion of Calibration for Transductive Confidence Machine with Limited Feedback. In: Gavaldá, R., Jantke, K.P., Takimoto, E. (eds) Algorithmic Learning Theory. ALT 2003. Lecture Notes in Computer Science(), vol 2842. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39624-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-540-39624-6_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20291-2
Online ISBN: 978-3-540-39624-6
eBook Packages: Springer Book Archive