基于不可分核的信息论学习
Information Theoretic Learning with Infinitely Divisible Kernels
摘要:
在本文中,我们开发了一个基于无限可分矩阵的信息理论学习框架。我们制定了一个熵的功能正定矩阵的基础上Renyi的公理定义的熵和检查这个功能,导致无限整除的概念的一些关键属性。该公式避免了密度的插件估计,并带来了再生核希尔伯特空间的表示能力。作为一个应用例子,我们得到一个监督度量学习算法使用基于矩阵的模拟条件熵实现的结果与最先进的国家。
英文摘要:
In this paper, we develop a framework for information theoretic learning based on infinitely divisible matrices. We formulate an entropy-like functional on positive definite matrices based on Renyi's axiomatic definition of entropy and examine some key properties of this functional that lead to the concept of infinite divisibility. The proposed formulation avoids the plug in estimation of density and brings along the representation power of reproducing kernel Hilbert spaces. As an application example, we derive a supervised metric learning algorithm using a matrix based analogue to conditional entropy achieving results comparable with the state of the art.
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。