一种新型高斯极小-极大定理及其应用
A Novel Gaussian Min-Max Theorem and its Applications
AI总结:
本文提出了一对满足 Gordon 比较不等式的新高斯过程,将经典的高斯极小-极大定理(GMT)和凸高斯极小-极大定理(CGMT)扩展至底层高斯矩阵行独立但非同分布的情形,并应用于多源高斯回归与高斯混合模型二分类。
摘要:
Gordon 的一个著名结果允许在满足某些不等式条件时比较两个高斯过程的极小-极大行为。该结果的推论包括高斯极小-极大定理(GMT)和凸高斯极小-极大定理(CGMT),它们在高维统计、机器学习、非光滑优化和信号处理中具有深远影响。这两个定理都依赖于 Slepian 首次识别的一对满足 Gordon 比较不等式的高斯过程。在本文中,我们识别出了这样一对新过程。由此产生的定理将经典的 GMT 和 CGMT 定理从主过程中底层高斯矩阵具有独立同分布行的情况扩展到具有独立但非同分布行的情况。新的 CGMT 被应用于多源高斯回归问题,以及一般高斯混合模型的二分类问题。
英文摘要:
A celebrated result by Gordon allows one to compare the min-max behavior of two Gaussian processes if certain inequality conditions are met. The consequences of this result include the Gaussian min-max (GMT) and convex Gaussian min-max (CGMT) theorems which have had far-reaching implications in high-dimensional statistics, machine learning, non-smooth optimization, and signal processing. Both theorems rely on a pair of Gaussian processes, first identified by Slepian, that satisfy Gordon's comparison inequalities. In this paper, we identify such a new pair. The resulting theorems extend the classical GMT and CGMT Theorems from the case where the underlying Gaussian matrix in the primary process has iid rows to where it has independent but non-identically-distributed ones. The new CGMT is applied to the problems of multi-source Gaussian regression, as well as to binary classification of general Gaussian mixture models.
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。