Non-asymptotic calibration and resolution

Authors:
Vladimir Vovk
Affiliations:
Computer Learning Research Centre, Department of Computer Science, Royal Holloway, University of London, Egham, Surrey, England
Venue:
ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory
Year:
2005

Citing 2
Cited 5

How to use expert advice

Journal of the ACM (JACM)
On the influence of the kernel on the consistency of support vector machines

The Journal of Machine Learning Research

Non-asymptotic calibration and resolution

Theoretical Computer Science
Deterministic calibration and Nash equilibrium

Journal of Computer and System Sciences
Leading strategies in competitive on-line prediction

Theoretical Computer Science
Leading strategies in competitive on-line prediction

ALT'06 Proceedings of the 17th international conference on Algorithmic Learning Theory
On-Line regression competitive with reproducing kernel hilbert spaces

TAMC'06 Proceedings of the Third international conference on Theory and Applications of Models of Computation

Quantified Score

Hi-index	0.01

Visualization

Abstract

We analyze a new algorithm for probability forecasting of binary labels, without making any assumptions about the way the data is generated. The algorithm is shown to be well calibrated and to have high resolution for big enough data sets and for a suitable choice of its parameter, a kernel on the Cartesian product of the forecast space [0,1] and the object space. Our results are non-asymptotic: we establish explicit inequalities for the performance of the algorithm.