熵协方差模型
Entropic covariance models
AI总结:
本文提出对协方差矩阵多种变换施加线性约束的通用框架,通过凸优化得到 $M$-估计量,并恢复 $\sqrt{n/d}$ 速率。
摘要:
在协方差矩阵估计中,挑战之一在于找到合适的模型和高效的估计方法。文献中两种常用的建模方法涉及对协方差矩阵或其逆矩阵施加线性约束。另一种方法考虑对协方差矩阵的矩阵对数施加线性约束。本文中,我们提出了一个对协方差矩阵的不同变换施加线性约束的通用框架,其中包括上述例子。我们提出的估计方法求解一个凸问题,并产生一个 $M$-估计量,使得相对直接的渐近分析(一般情形)和有限样本分析(Gauss 情形)成为可能。特别地,我们恢复了标准的 $\sqrt{n/d}$ 速率,其中 $d$ 是底层模型的维数。我们的几何洞见使得扩展协方差矩阵建模中的各种近期结果成为可能。这包括提供相关矩阵空间的无约束参数化,作为利用矩阵对数的近期结果的一种替代方案。
英文摘要:
In covariance matrix estimation, one of the challenges lies in finding a suitable model and an efficient estimation method. Two commonly used modelling approaches in the literature involve imposing linear restrictions on the covariance matrix or its inverse. Another approach considers linear restrictions on the matrix logarithm of the covariance matrix. In this paper, we present a general framework for linear restrictions on different transformations of the covariance matrix, including the mentioned examples. Our proposed estimation method solves a convex problem and yields an $M$-estimator, allowing for relatively straightforward asymptotic (in general) and finite sample analysis (in the Gaussian case). In particular, we recover standard $\sqrt{n/d}$ rates, where $d$ is the dimension of the underlying model. Our geometric insights allow to extend various recent results in covariance matrix modelling. This includes providing unrestricted parametrizations of the space of correlation matrices, which is alternative to a recent result utilizing the matrix logarithm.
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。