Parameter Identifiability in Statistical Machine Learning: A Review

doi:10.1162/NECO_a_00947

	Parameter Identifiability in Statistical Machine Learning: A Review
	Ran, Zhi-Yong 1; Hu, Bao-Gang2
发表期刊	NEURAL COMPUTATION
	2017-05-01
卷号	29 期号:5 页码:1151-1203
文章类型	Review
摘要	This review examines the relevance of parameter identifiability for statistical models used in machine learning. In addition to defining main concepts, we address several issues of identifiability closely related to machine learning, showing the advantages and disadvantages of state-of- the-art research and demonstrating recent progress. First, we review criteria for determining the parameter structure of models from the literature. This has three related issues: parameter identifiability, parameter redundancy, and reparameterization. Second, we review the deep influence of identifiability on various aspects of machine learning from theoretical and application viewpoints. In addition to illustrating the utility and influence of identifiability, we emphasize the interplay among identifiability theory, machine learning, mathematical statistics, information theory, optimization theory, information geometry, Riemann geometry, symbolic computation, Bayesian inference, algebraic geometry, and others. Finally, we present a new perspective together with the associated challenges.
关键词	Parameter Identifiability Statistical Machine Learning
WOS标题词	Science & Technology ; Technology ; Life Sciences & Biomedicine
DOI	10.1162/NECO_a_00947
关键词[WOS]	NATURAL GRADIENT DESCENT ; MULTILAYER NEURAL-NETWORKS ; SOFT COMMITTEE MACHINES ; INFORMATION CRITERION ; STRUCTURAL IDENTIFIABILITY ; COMPARTMENTAL-MODELS ; COMPUTER ALGEBRA ; LIKELIHOOD RATIO ; HIDDEN UNITS ; SINGULARITIES
收录类别	SCI ; SSCi
语种	英语
项目资助者	NSFC(61273196 ; 61620106003)
WOS研究方向	Computer Science ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Neurosciences
WOS记录号	WOS:000399679500001
引用统计	被引频次：16[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/15089
专题	多模态人工智能系统全国重点实验室_多媒体计算
作者单位	1.Chongqing Univ Posts & Telecommun, Chongqing Key Lab Computat Intelligence, Sch Comp Sci & Technol, Chongqing 400065, Peoples R China 2.Chinese Acad Sci, Inst Automat, NLPR & LIAMA, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Ran, Zhi-Yong,Hu, Bao-Gang. Parameter Identifiability in Statistical Machine Learning: A Review[J]. NEURAL COMPUTATION,2017,29(5):1151-1203.
APA	Ran, Zhi-Yong,&Hu, Bao-Gang.(2017).Parameter Identifiability in Statistical Machine Learning: A Review.NEURAL COMPUTATION,29(5),1151-1203.
MLA	Ran, Zhi-Yong,et al."Parameter Identifiability in Statistical Machine Learning: A Review".NEURAL COMPUTATION 29.5(2017):1151-1203.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Ran17.pdf（466KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载