Low-Rank Covariance Function Estimation for Multidimensional Functional Data

Low-Rank Covariance Function Estimation for Multidimensional Functional Data
复制标题

多维函数数据的低秩协方差函数估计

DOI:
10.1080/01621459.2020.1820344
复制
发表时间:
2020
影响因子:
3.7
通讯作者:
Zhang, Xiaoke
Zhang, Xiaoke
中科院分区:
数学1区
文献类型:
--
作者:
Wang, Jiayi;Wong, Raymond K.;Zhang, Xiaoke

文献摘要

参考文献

被引文献

相似文献

如今,多维函数数据出现在许多领域。协方差函数在分析此类日益常见的数据中发挥着重要作用。在本文中,我们在再现核希尔伯特空间(RKHS)的框架下提出了一种新颖的非参数协方差函数估计方法,可以处理稀疏和稠密的函数数据。我们将(有限维)张量的多线性秩结构扩展到函数,这允许对协方差算子和边际结构进行灵活建模。所提出的框架可以保证所得到的估计器是自动半正定的,并且可以合并各种谱正则化。迹范数正则化尤其可以促进协方差算子和边际结构的低秩。尽管缺乏封闭形式,但在温和的假设下,所提出的估计器可以实现统一的理论结果,该结果适用于样本大小和每个样本域的观测数量之间的任何相对大小,并且收敛速度揭示了从稀疏函数数据到稠密函数数据的相变现象。基于新的表示定理,开发了一种用于迹范数正则化的 ADMM 算法。仿真研究和 Argo 项目数据集的分析证明了所提出的估计器具有吸引力的数值性能。本文的补充材料可在线获取。
Multidimensional function data arise from many fields nowadays. The covariance function plays an important role in the analysis of such increasingly common data. In this article, we propose a novel nonparametric covariance function estimation approach under the framework of reproducing kernel Hilbert spaces (RKHS) that can handle both sparse and dense functional data. We extend multilinear rank structures for (finite-dimensional) tensors to functions, which allow for flexible modeling of both covariance operators and marginal structures. The proposed framework can guarantee that the resulting estimator is automatically semipositive definite, and can incorporate various spectral regularizations. The trace-norm regularization in particular can promote low ranks for both covariance operator and marginal structures. Despite the lack of a closed form, under mild assumptions, the proposed estimator can achieve unified theoretical results that hold for any relative magnitudes between the sample size and the number of observations per sample field, and the rate of convergence reveals the phase-transition phenomenon from sparse to dense functional data. Based on a new representer theorem, an ADMM algorithm is developed for the trace-norm regularization. The appealing numerical performance of the proposed estimator is demonstrated by a simulation study and the analysis of a dataset from the Argo project. Supplementary materials for this article are available online.
DOI: --
发表时间: 2018
期刊: --
影响因子: --
作者:
Raymond K. W. Wong;Xiaoke Zhang
通讯作者: Raymond K. W. Wong;Xiaoke Zhang
DOI: 10.1080/01621459.2017.1356320
发表时间: 2018-01-01
影响因子: 3.7
作者:
Sun, Xiaoxiao;Du, Pang;Ma, Ping
通讯作者: Ma, Ping
DOI: 10.1198/000313006x124541
发表时间: 2006-08
期刊: The American Statistician
影响因子: --
作者:
N. D. Pearce;M. Wand
通讯作者: N. D. Pearce;M. Wand
DOI: 10.1214/16-aos1475
发表时间: 2017-06-01
影响因子: 4.5
作者:
Li, Bing;Song, Jun
通讯作者: Song, Jun
纵向和多维函数数据的贝叶斯分析。
DOI: 10.1093/biostatistics/kxaa041
发表时间: 2022
期刊: Biostatistics (Oxford, England)
影响因子: --
作者:
Shamshoian,John;Şentürk,Damla;Jeste,Shafali;Telesca,Donatello
通讯作者: Telesca,Donatello