Result: Well-calibrated predictions from on-line compression models

Title:
Well-calibrated predictions from on-line compression models
Authors:
Source:
Algorithmic learning theoryTheoretical computer science. 364(1):10-26
Publisher Information:
Amsterdam: Elsevier, 2006.
Publication Year:
2006
Physical Description:
print, 32 ref
Original Material:
INIST-CNRS
Document Type:
Conference Conference Paper
File Description:
text
Language:
English
Author Affiliations:
Computer Learning Research Centre, Department of Computer Silence, Royal Holloway, University of London, Egham, Surrey TW20 0EX, United Kingdom
ISSN:
0304-3975
Rights:
Copyright 2006 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Computer science; theoretical automation; systems
Accession Number:
edscal.18267548
Database:
PASCAL Archive

Further Information

It has been shown recently that transductive confidence machine (TCM) is automatically well-calibrated when used in the on-line mode and provided that the data sequence is generated by an exchangeable distribution. In this paper we strengthen this result by relaxing the assumption of exchangeability of the data-generating distribution to the much weaker assumption that the data agrees with a given on-line compression model.