Model selection via the VC dimension

MaRDI QIDQ5214172zbMATH OpenFDO

Authors Merlin Mpoudeu, Bertrand S. Clarke

Publication date 7 February 2020

Full work available at URL https://arxiv.org/abs/1808.05296, http://jmlr.csail.mit.edu/papers/v20/17-669.html

zbMATH Keywords

Bayesian information criterionempirical risk minimizationmodel selectionmulti-type datasparsity methodsVapnik-Chervonenkis dimension

Mathematics Subject Classification ID

Asymptotic properties of parametric tests (62F05) Asymptotic properties of parametric estimators (62F12) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: We derive an objective function that can be optimized to give an estimator of the Vapnik- Chervonenkis dimension for model selection in regression problems. We verify our estimator is consistent. Then, we verify it performs well compared to seven other model selection techniques. We do this for a variety of types of data sets.

Recommendations

• Comparison of Model Selection for Regression
• Model complexity control and statistical learning theory
• SVM Model Selection with the VC Bound
• Adaptive model selection using empirical complexities
• scientific article; zbMATH DE number 1321826

Cites work

• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 1432028 (Why is no real title available?)
• scientific article; zbMATH DE number 3391741 (Why is no real title available?)
• Machine learning. A probabilistic perspective
• Minimum complexity density estimation
• Model selection via the VC dimension
• Neural Network Learning
• Sure independence screening for ultrahigh dimensional feature space. With discussion and authors' reply
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties

Cited in

(4)

• Model complexity control and statistical learning theory
• VC-dimension and structural risk minimization for the analysis of nonlinear ecological models
• Comparison of Model Selection for Regression
• Model selection via the VC dimension

This page was built for publication: Model selection via the VC dimension

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5214172)