Online Bayesian learning for mixtures of spatial spline regressions with mixed effects

doi:10.1080/00949655.2021.2002329

	Online Bayesian learning for mixtures of spatial spline regressions with mixed effects
	Ge, Shufei1 ; Wang, Shijia 2,3; Nathoo, Farouk S.4; Wang, Liangliang 5
	2022-05-03
发表期刊	JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION (IF:1.1[JCR-2023],1.3[5-Year])
ISSN	0094-9655
EISSN	1563-5163
DOI	10.1080/00949655.2021.2002329
摘要	Classification and clustering methods based on univariate functions have been well developed. Recent work has extended the techniques to the domain of bivariate functions by incorporating the techniques based on mixtures of spatial spline regression with mixed-effects models. An Expectation Maximization (EM) algorithm is implemented to facilitate model inference. In this paper, we further extend the mixtures of spatial spline regression with mixed-effects model under the Bayesian framework to accommodate streaming image data. First, we derive a Markov chain Monte Carlo (MCMC) algorithm as an alternative approach to the EM algorithm to make inference on the model. However, MCMC is not scalable to streaming image data since it requires all observed information to update the posterior distribution of the parameters. To tackle this issue, we propose a sequential Monte Carlo (SMC) algorithm to analyse online fashion image data. The existence of model sufficient statistics improves the efficiency of the proposed online SMC algorithm. Instead of saving all batch data for inference, we only require storage of the model sufficient statistics and every data point is only used once, which is well suited for large-scale stream type data. In addition, the proposed algorithm provides an unbiased estimator of the marginal likelihood as a by-product of the approach, which can be used for model selection. Numerical experiments are used to demonstrate the effectiveness of our method. Our implementation is available at https://github.com/ShufeiGe/Online-Bayesian-learning-for-MMSRm.
关键词	Online learning sequential Monte Carlo functional data analysis
收录类别	SCIE
语种	英语
WOS研究方向	Computer Science ; Mathematics
WOS类目	Computer Science, Interdisciplinary Applications ; Statistics & Probability
WOS记录号	WOS:000722094000001
出版者	TAYLOR & FRANCIS LTD
原始文献类型	Article; Early Access
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/133142
专题	数学科学研究所_PI研究组(P)_葛淑菲组
通讯作者	Wang, Shijia; Wang, Liangliang
作者单位	1.ShanghaiTech Univ, Inst Math Sci, Shanghai, Peoples R China; 2.Nankai Univ, Sch Stat & Data Sci, LPMC, Tianjin, Peoples R China; 3.Nankai Univ, KLMDASR, Tianjin, Peoples R China; 4.Univ Victoria, Dept Math & Stat, Victoria, BC, Canada; 5.Simon Fraser Univ, Dept Stat & Actuarial Sci, Burnaby, BC, Canada
第一作者单位	数学科学研究所
第一作者的第一单位	数学科学研究所
推荐引用方式 GB/T 7714	Ge, Shufei,Wang, Shijia,Nathoo, Farouk S.,et al. Online Bayesian learning for mixtures of spatial spline regressions with mixed effects[J]. JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION,2022.
APA	Ge, Shufei,Wang, Shijia,Nathoo, Farouk S.,&Wang, Liangliang.(2022).Online Bayesian learning for mixtures of spatial spline regressions with mixed effects.JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION.
MLA	Ge, Shufei,et al."Online Bayesian learning for mixtures of spatial spline regressions with mixed effects".JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION (2022).