面向一般加性噪声矩阵的矩形旋转不变估计器
Rectangular Rotational Invariant Estimator for General Additive Noise Matrices
AI总结:
本文提出矩形旋转不变估计器以恢复受任意加性旋转不变噪声污染的实矩阵,推导渐近 MMSE、Gaussian 噪声显式式及互信息公式,并经数值验证。
摘要:
我们提出一种矩形旋转不变估计器,用于在大维数极限下,从受任意加性旋转不变扰动影响的含噪矩阵观测中恢复一个实矩阵。利用该估计器的 Bayes 最优性,我们推导出渐近最小均方误差(MMSE)。对于 Gaussian 噪声这一特定情形,我们依据观测矩阵的极限奇异值分布得到了 MMSE 的显式表达式。此外,我们证明了一个将渐近互信息与矩形矩阵的对数球面积分极限联系起来的公式。我们还对所得结果进行了数值检验,结果与理论预测及已知 Bayesian 推断结果相符。
英文摘要:
We propose a rectangular rotational invariant estimator to recover a real matrix from noisy matrix observations coming from an arbitrary additive rotational invariant perturbation, in the large dimension limit. Using the Bayes-optimality of this estimator, we derive the asymptotic minimum mean squared error (MMSE). For the particular case of Gaussian noise, we find an explicit expression for the MMSE in terms of the limiting singular value distribution of the observation matrix. Moreover, we prove a formula linking the asymptotic mutual information and the limit of log-spherical integral of rectangular matrices. We also provide numerical checks for our results, which match our theoretical predictions and known Bayesian inference results.
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。