Probability (2nd ed.)
Comparing the Bayes and Typicalness Frameworks
EMCL '01 Proceedings of the 12th European Conference on Machine Learning
On-Line Confidence Machines Are Well-Calibrated
FOCS '02 Proceedings of the 43rd Symposium on Foundations of Computer Science
Machine-Learning Applications of Algorithmic Randomness
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Transduction with confidence and credibility
IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
A Universal Well-Calibrated Algorithm for On-line Classification
The Journal of Machine Learning Research
Well-calibrated predictions from on-line compression models
Theoretical Computer Science - Algorithmic learning theory
Using a similarity measure for credible classification
Discrete Applied Mathematics
| Hi-index | 0.00 |
Transductive Confidence Machine (TCM) is a way of converting standard machine-learning algorithms into algorithms that output predictive regions rather than point predictions. It has been shown recently that TCM is well-calibrated when used in the on-line mode: at any confidence level 1 - 驴, the long-run relative frequency of errors is guaranteed not to exceed 驴 provided the examples are generated independently from the same probability distribution P. Therefore, the number of "uncertain" predictive regions (i.e., those containing more than one label) becomes the sole measure of performance. The main result of this paper is that for any probability distribution P (assumed to generate the examples), it is possible to construct a TCM (guaranteed to be well-calibrated even if the assumption is wrong) that performs asymptotically as well as the best region predictor under P.