论文标题
监督分类的广义最大熵
Generalized Maximum Entropy for Supervised Classification
论文作者
论文摘要
最大的熵原则提倡使用分布来评估事件的概率，从而最大化满足某些期望约束的熵。可以将这种原则推广到与Minimax方法相对应的任意决策问题。本文根据导致最小风险分类器（MRC）的广义最大熵原理建立了一个监督分类的框架。我们开发了确定通用熵功能的MRC的学习技术，并通过凸优化提供了绩效。此外，我们描述了提出的技术与现有分类方法的关系，并与所提出的界限和常规方法相比，量化MRCS性能。
The maximum entropy principle advocates to evaluate events' probabilities using a distribution that maximizes entropy among those that satisfy certain expectations' constraints. Such principle can be generalized for arbitrary decision problems where it corresponds to minimax approaches. This paper establishes a framework for supervised classification based on the generalized maximum entropy principle that leads to minimax risk classifiers (MRCs). We develop learning techniques that determine MRCs for general entropy functions and provide performance guarantees by means of convex optimization. In addition, we describe the relationship of the presented techniques with existing classification methods, and quantify MRCs performance in comparison with the proposed bounds and conventional methods.
