风险界限的估计VC维度
Estimated VC dimension for risk bounds
摘要:
Vapnik-Chervonenkis(VC)维是学习算法泛化能力的基本度量。然而,除了少数特殊情况外,很难或不可能进行分析计算。Vapnik等人。[10]提出了一种凭经验估计VC维度的技术。虽然他们的方法在模拟中表现良好,但它不能用于限制分类器的泛化风险,因为VC维本身的估计误差没有界限。我们纠正这一遗漏,提供高概率浓度的结果,建议的估计和推导相应的泛化界。
英文摘要:
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 rectify this omission, providing high probability concentration results for the proposed estimator and deriving corresponding generalization bounds.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。