Towards robust model selection using estimation and approximation error bounds

Joel Ratsaby, Ronny Meir, Vitaly Maiorov

Research output: Contribution to conferencePaperpeer-review

6 Scopus citations

Abstract

One of the main problems in machine learning and statistical inference is selecting an appropriate model by which a set of data can be explained. A novel model selection criterion based on the uniform convergence of empirical processes combined with the results concerning the approximation ability of non-linear manifolds of functions is introduced. A coherent and robust framework for model selection was elucidated and a lower bound on the approximation error was established, giving a well specified sense for most functions of interest.

Original languageEnglish
Pages57-67
Number of pages11
DOIs
StatePublished - 1 Jan 1996
Externally publishedYes
EventProceedings of the 1996 9th Annual Conference on Computational Learning Theory - Desenzano del Garda, Italy
Duration: 28 Jun 19961 Jul 1996

Conference

ConferenceProceedings of the 1996 9th Annual Conference on Computational Learning Theory
CityDesenzano del Garda, Italy
Period28/06/961/07/96

Fingerprint

Dive into the research topics of 'Towards robust model selection using estimation and approximation error bounds'. Together they form a unique fingerprint.

Cite this