Vapnik V N
AT&T Labs-Research, Red Bank, NJ 07701, USA.
IEEE Trans Neural Netw. 1999;10(5):988-99. doi: 10.1109/72.788640.
Statistical learning theory was introduced in the late 1960's. Until the 1990's it was a purely theoretical analysis of the problem of function estimation from a given collection of data. In the middle of the 1990's new types of learning algorithms (called support vector machines) based on the developed theory were proposed. This made statistical learning theory not only a tool for the theoretical analysis but also a tool for creating practical algorithms for estimating multidimensional functions. This article presents a very general overview of statistical learning theory including both theoretical and algorithmic aspects of the theory. The goal of this overview is to demonstrate how the abstract learning theory established conditions for generalization which are more general than those discussed in classical statistical paradigms and how the understanding of these conditions inspired new algorithmic approaches to function estimation problems. A more detailed overview of the theory (without proofs) can be found in Vapnik (1995). In Vapnik (1998) one can find detailed description of the theory (including proofs).
统计学习理论于20世纪60年代末被引入。直到20世纪90年代，它一直是对从给定数据集中进行函数估计问题的纯理论分析。20世纪90年代中期，基于已发展理论提出了新型学习算法（称为支持向量机）。这使得统计学习理论不仅成为理论分析的工具，还成为创建用于估计多维函数的实用算法的工具。本文对统计学习理论进行了非常全面的概述，包括该理论的理论和算法方面。此概述的目的是展示抽象学习理论如何建立比经典统计范式中讨论的更通用的泛化条件，以及对这些条件的理解如何激发了针对函数估计问题的新算法方法。该理论更详细的概述（无证明）可在Vapnik（1995）中找到。在Vapnik（1998）中可以找到该理论的详细描述（包括证明）。
