arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.02119stat.MLcs.LGmath.PRmath.STstat.TH
收藏

数据增强在精度矩阵估计中的非渐近分析

Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation

Qube Research and Technologies(Qube研究与技术公司);École Polytechnique(巴黎综合理工学院)

Lucas Morisset, Adrien Hardy, Alain Durmus

AI总结:

本文研究了数据增强在高维精度矩阵估计中的非渐近分析,提出了一种新的确定性等价方法,并通过实验验证了理论结果。

摘要:

本文针对高维设置下的逆协方差(也称为精度矩阵)估计问题进行了研究。具体而言,我们专注于两类估计器:具有目标矩阵成比例于单位矩阵的线性收缩估计器,以及从数据增强(DA)导出的估计器。在此,DA指的是在模型拟合之前,通过生成模型或对原始数据进行随机变换来丰富数据集的常见做法。对于这两类估计器,我们推导了估计器并提供了其二次误差的集中界。这使得可以进行方法比较和超参数调整,例如选择最优的人工样本比例。在技术层面,我们的分析依赖于随机矩阵理论的工具。我们引入了一个新的确定性等价于广义残差矩阵,以适应具有特定结构的依赖样本。我们通过数值实验支持我们的理论结果。

英文摘要:

This paper addresses the problem of inverse covariance (also known as precision matrix) estimation in high-dimensional settings. Specifically, we focus on two classes of estimators: linear shrinkage estimators with a target proportional to the identity matrix, and estimators derived from data augmentation (DA). Here, DA refers to the common practice of enriching a dataset with artificial samples--typically generated via a generative model or through random transformations of the original data--prior to model fitting. For both classes of estimators, we derive estimators and provide concentration bounds for their quadratic error. This allows for both method comparison and hyperparameter tuning, such as selecting the optimal proportion of artificial samples. On the technical side, our analysis relies on tools from random matrix theory. We introduce a novel deterministic equivalent for generalized resolvent matrices, accommodating dependent samples with specific structure. We support our theoretical results with numerical experiments.

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。

↑