dc.contributor.author | Wang, Yong | |
dc.contributor.author | Witten, Ian H. | |
dc.coverage.spatial | Conference held at University of NSW, Sydney, Australia | en_NZ |
dc.date.accessioned | 2009-04-29T00:24:52Z | |
dc.date.available | 2009-04-29T00:24:52Z | |
dc.date.issued | 2002 | |
dc.identifier.citation | Wang, Y. & Witten, I.H. (2002). Modeling for optimal probability prediction. In Proceedings of the Nineteenth International Conference on Machine Learning, Sydney, Australia, July (pp. 650-657). San Francisco: Morgan Kaufmann Publishers Inc. | en |
dc.identifier.uri | https://hdl.handle.net/10289/2131 | |
dc.description.abstract | We present a general modelling method for optimal probability prediction over future observations, in which model dimensionality is determined as a natural by-product. This new method yields several estimators, and we establish theoretically that they are optimal (either overall or under stated restrictions) when the number of free parameters is infinite. As a case study, we investigate the problem of fitting logistic models in finite-sample situations. Simulation results on both artificial and practical datasets are supportive. | en |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | |
dc.publisher | Morgan Kaufmann Publishers Inc. | en |
dc.rights | This is the author’s version of a conference paper published in Proceedings of the Nineteenth International Conference on Machine Learning, Sydney, Australia, July. ©2002 Authors | en |
dc.subject | computer science | en |
dc.subject | Machine learning | |
dc.title | Modeling for optimal probability prediction | en |
dc.type | Conference Contribution | en |
dc.relation.isPartOf | ICML | en_NZ |
pubs.begin-page | 650 | en_NZ |
pubs.elements-id | 11786 | |
pubs.end-page | 657 | en_NZ |
pubs.finish-date | 2002-07-12 | en_NZ |
pubs.place-of-publication | San Francisco, California | en_NZ |
pubs.start-date | 2002-07-08 | en_NZ |
pubs.volume | Proc. Nineteenth International Conference on Machine Learning | en_NZ |