Nonstationary Modeling With Sparsity for Spatial Data via the Basis Graphical Lasso

Nonstationary Modeling With Sparsity for Spatial Data via the Basis Graphical Lasso
复制标题

通过基本图形套索对空间数据进行稀疏性非平稳建模

DOI:
10.1080/10618600.2020.1811103
复制
发表时间:
2021
影响因子:
2.4
通讯作者:
Becker, Stephen
Becker, Stephen
中科院分区:
数学2区
文献类型:
--
作者:
Krock, Mitchell;Kleiber, William;Becker, Stephen

文献摘要

参考文献

被引文献

相似文献

许多现代空间模型将随机变化分量表示为具有随机系数的基展开。低秩模型,近似谱分解,多分辨率表示,随机偏微分方程和经验正交函数都属于这个基本框架。给定特定的基础,随机依赖依赖于系数的灵活建模。在高斯假设下,我们提出了一个图形化的模型家庭的随机系数参数化的精度矩阵。稀疏的精度矩阵是鼓励使用惩罚似然框架,我们称这种方法的基础图形套索。计算遵循优化-最小化(MM)方法,其副产品是与标准图形套索的连接。其结果是一个灵活的非平稳空间模型,适用于非常大的数据集与多个实现。我们将该模型应用于统计气候学中的两个大型异构空间数据集,并恢复物理上合理的图形结构。此外,该模型在预测交叉验证中与流行的LatticeKrig模型竞争,但提高了Akaike信息标准得分和联合预测分布质量的对数得分。
Many modern spatial models express the stochastic variation component as a basis expansion with random coefficients. Low rank models, approximate spectral decompositions, multiresolution representations, stochastic partial differential equations, and empirical orthogonal functions all fall within this basic framework. Given a particular basis, stochastic dependence relies on flexible modeling of the coefficients. Under a Gaussianity assumption, we propose a graphical model family for the stochastic coefficients by parameterizing the precision matrix. Sparsity in the precision matrix is encouraged using a penalized likelihood framework—we term this approach the basis graphical lasso. Computations follow from a majorization-minimization (MM) approach, a byproduct of which is a connection to the standard graphical lasso. The result is a flexible nonstationary spatial model that is adaptable to very large datasets with multiple realizations. We apply the model to two large and heterogeneous spatial datasets in statistical climatology and recover physically sensible graphical structures. Moreover, the model performs competitively against the popular LatticeKrig model in predictive cross-validation but improves the Akaike information criterion score and a log score for the quality of the joint predictive distribution.
DOI: 10.1093/biomet/89.1.197
发表时间: 2002-03-01
期刊: BIOMETRIKA
影响因子: 2.7
作者:
Fuentes, M
通讯作者: Fuentes, M
DOI: 10.1093/biomet/asr054
发表时间: 2011-12-01
期刊: BIOMETRIKA
影响因子: 2.7
作者:
Bien, Jacob;Tibshirani, Robert J.
通讯作者: Tibshirani, Robert J.
用于将高斯随机场模型拟合到大型数据集的稀疏精度矩阵选择
DOI: --
发表时间: 2014
期刊:
影响因子: --
作者:
S. Tajbakhsh;N. Aybat;E. Castillo
通讯作者: E. Castillo
DOI: 10.1214/07-aoas131
发表时间: 2007-12-01
影响因子: 1.8
作者:
Friedman, Jerome;Hastie, Trevor;Tibshirani, Robert
通讯作者: Tibshirani, Robert
用于学习大规模稀疏图形模型的线性时间算法
DOI: --
发表时间: 2019
期刊: IEEE access
影响因子: 3.9
作者:
Fattahi, Salar;Zhang, Richard;Sojoudi, Somayeh
通讯作者: Sojoudi, Somayeh