You are currently offline. Some features of the site may not work correctly.

Corpus ID: 88518913

Estimated VC dimension for risk bounds

@article{McDonald2011EstimatedVD,
title={Estimated VC dimension for risk bounds},
author={D. J. McDonald and C. Shalizi and M. Schervish},
journal={arXiv: Machine Learning},
year={2011}
}

Vapnik-Chervonenkis (VC) dimension is a fundamental measure of the generalization capacity of learning algorithms. However, apart from a few special cases, it is hard or impossible to calculate analytically. Vapnik et al. [10] proposed a technique for estimating the VC dimension empirically. While their approach behaves well in simulations, it could not be used to bound the generalization risk of classifiers, because there were no bounds for the estimation error of the VC dimension itself. We… CONTINUE READING