Universal well-calibrated algorithm for on-line classification

Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

Volumn 2777, Issue , 2003, Pages 358-372

  Vovk, Vladimir ^a  

^a UNIVERSITY OF LONDON   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; CALIBRATION; CLASSIFICATION (OF INFORMATION); DATA ACQUISITION; ERROR ANALYSIS; LEARNING SYSTEMS; PROBABILITY DISTRIBUTIONS; PROBLEM SOLVING; FORECASTING;

ON-LINE CLASSIFICATION; RANDOMIZATION; TRANSDUCTIVE CONFIDENCE MACHINE (TCM); WELL-CALIBRATED ALGORITHM; CONFIDENCE LEVELS; PREDICTION ALGORITHMS; PREDICTIVE PERFORMANCE; RELATIVE FREQUENCIES;

ONLINE SYSTEMS; ALGORITHMS;

EID: 9444241474     PISSN: 03029743     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1007/978-3-540-45167-9_27     Document Type: Conference Paper

References (11)

1. Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, and Clifford Stein. Introduction to Algorithms. MIT Press, Cambridge, MA, second edition, 2001.
2. David R. Cox and David V. Hinkley. Theoretical Statistics. Chapman and Hall, London, 1974.
3. Luc Devroye, László Györfi, and Gábor Lugosi. A Probabilistic Theory of Pattern Recognition. Springer, New York, 1996.
4. Yoav Freund, Yishay Mansour, and Robert E. Schapire. Generalization bounds for averaged classifiers. July 2002. To appear in Annals of Statistics.
5. Ronald L. Rivest and R. Sloan. Learning complicated concepts reliably and usefully. In Proceedings of the First Annual Conference on Computational Learning Theory, pages 69-79, San Mateo, CA, 1988. Morgan Kaufmann.
6. Craig Saunders, Alex Gammerman, and Vladimir Vovk. Transduction with confidence and credibility. In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, pages 722-726, 1999.
7. Albert N. Shiryaev. Probability. Springer, New York, second edition, 1996.
8. Vladimir Vovk. Asymptotic optimality of Transductive Confidence Machine. In Proceedings of the Thirteenth International Conference on Algorithmic Learning Theory, volume 2533 of Lecture Notes in Artificial Intelligence, pages 336-350, 2002.
9. Vladimir Vovk. On-line Confidence Machines are well-calibrated. In Proceedings of the Forty Third Annual Symposium on Foundations of Computer Science, pages 187-196. IEEE Computer Society, 2002.
10. Vladimir Vovk. Universal well-calibrated algorithm for on-line classification, Online Compression Modelling project, http://vovk.net/kp, Working Paper #3, November 2002.
11. Vladimir Vovk, Alex Gammerman, and Craig Saunders. Machine-learning applications of algorithmic randomness. In Proceedings of the Sixteenth International Conference on Machine Learning, pages 444-453, San Francisco, CA, 1999. Morgan Kaufmann.