线性、多项式、二次和圆锥边知识学习的泛化界
Generalization Bounds for Learning with Linear, Polygonal, Quadratic and Conic Side Knowledge
摘要:
在本文中,我们考虑了一个监督学习设置,其中提供了关于未标记示例的标签的边知识。边知识具有减小假设空间的效果,导致更紧的泛化界,从而可能更好的泛化。我们考虑几种类型的边知识,第一个导致线性和多边形的约束的假设空间,第二个导致二次约束,最后导致圆锥约束。我们展示了如何不同类型的领域知识可以直接导致这些种类的边知识。我们证明了二次和圆锥边知识的假设空间的复杂性措施的界限,并表明这些界限是紧在一个特定的意义上的二次的情况下。
英文摘要:
In this paper, we consider a supervised learning setting where side knowledge is provided about the labels of unlabeled examples. The side knowledge has the effect of reducing the hypothesis space, leading to tighter generalization bounds, and thus possibly better generalization. We consider several types of side knowledge, the first leading to linear and polygonal constraints on the hypothesis space, the second leading to quadratic constraints, and the last leading to conic constraints. We show how different types of domain knowledge can lead directly to these kinds of side knowledge. We prove bounds on complexity measures of the hypothesis space for quadratic and conic side knowledge, and show that these bounds are tight in a specific sense for the quadratic case.
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。