|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
The 43rd Annual IEEE Symposium on Foundations of Computer Science (FOCS'02)
On-Line Confidence Machines Are Well-Calibrated
Vancouver, BC, Canada
November 16-November 19
ISBN: 0-7695-1822-2
| ASCII Text | x | ||
| Vladimir Vovk, "On-Line Confidence Machines Are Well-Calibrated," Foundations of Computer Science, IEEE Annual Symposium on, pp. 187, The 43rd Annual IEEE Symposium on Foundations of Computer Science (FOCS'02), 2002. | |||
| BibTex | x | ||
| @article{ 10.1109/SFCS.2002.1181895, author = {Vladimir Vovk}, title = {On-Line Confidence Machines Are Well-Calibrated}, journal ={Foundations of Computer Science, IEEE Annual Symposium on}, volume = {0}, year = {2002}, issn = {0272-5428}, pages = {187}, doi = {http://doi.ieeecomputersociety.org/10.1109/SFCS.2002.1181895}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Foundations of Computer Science, IEEE Annual Symposium on TI - On-Line Confidence Machines Are Well-Calibrated SN - 0272-5428 SP EP A1 - Vladimir Vovk, PY - 2002 KW - null VL - 0 JA - Foundations of Computer Science, IEEE Annual Symposium on ER - | |||
Transductive Confidence Machine (TCM) and its computationally efficient modification, Inductive Confidence Machine (ICM), are ways of complementing machine-learning algorithms with practically useful measures of confidence. We show that when TCM and ICM are used in the on-line mode, their confidence measures are well-calibrated, in the sense that predictive regions at confidence level 1 - \delta will be wrong with relative frequency at most \delta (approaching \delta in the case of randomised TCM and ICM) in the long run. This is not just an asymptotic phenomenon: actually the error probability of randomised TCM and ICM is \delta at every trial and errors happen independently at different trials.
Citation:
Vladimir Vovk, "On-Line Confidence Machines Are Well-Calibrated," focs, pp.187, The 43rd Annual IEEE Symposium on Foundations of Computer Science (FOCS'02), 2002
Usage of this product signifies your acceptance of the Terms of Use.