Model Selection via the VC-Dimension

08/15/2018

∙

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.

READ FULL TEXT

Model Selection via the VC-Dimension

Quasi-Maximum Likelihood based Model Selection Procedures for Binary Outcomes

Strongly Consistent of Kullback-Leibler Divergence Estimator and Tests for Model Selection Based on a Bias Reduced Kernel Density Estimator

Universal and Automatic Elbow Detection for Learning the Effective Number of Components in Model Selection Problems

Simultaneous Localization and Layout Model Selection in Manhattan Worlds

Model Selection using Multi-Objective Optimization

General model-free weighted envelope estimation

Model Selection by Loss Rank for Classification and Unsupervised Learning

Model Selection via the VC-Dimension

Related Research

Quasi-Maximum Likelihood based Model Selection Procedures for Binary Outcomes

Strongly Consistent of Kullback-Leibler Divergence Estimator and Tests for Model Selection Based on a Bias Reduced Kernel Density Estimator

Universal and Automatic Elbow Detection for Learning the Effective Number of Components in Model Selection Problems

Simultaneous Localization and Layout Model Selection in Manhattan Worlds

Model Selection using Multi-Objective Optimization

General model-free weighted envelope estimation

Model Selection by Loss Rank for Classification and Unsupervised Learning