自动化学报2017，Vol.43Issue(10)：1677-1686,10.DOI:10.16383/j.aas.2017.c160720
统计机器学习中参数可辨识性研究及其关键问题
Parameter Identifiability and Its Key Issues in Statistical Machine Learning
摘要
Abstract
The study of parameter identifiability has important theoretical meaning and practical value in statistical machine learning.Parameter identifiability is a property that concerns whether the model parameters can be uniquely determined.In learning models containing physical parameters,identifiability is a prerequisite for estimating those parameters;more importantly,it reflects the physical characteristic determined by those parameters.In order to extend our perspective to future human-like intelligent machines,we put the learning models into the framework of "knowledge-and data-driven models".Within this framework,we propose two key issues.The first is about identifiability criteria which aim to study various criteria closely related to identifiability;the coupling manner between knowledge-driven submodel and data-driven submodel provides novel topics for identifiability study.The second focuses on identifiability relevant to theory and application in machine learning;this involves the deep influence of identifiability on parameter estimation,model selection,learning algorithms,learning dynamics,Bayesian inference.关键词
可辨识性/统计机器学习/参数估计/奇异学习理论/贝叶斯推断Key words
Identifiability/statistical machine learning/parameter estimation/singular learning theory/Bayes inference引用本文复制引用
冉智勇,胡包钢..统计机器学习中参数可辨识性研究及其关键问题[J].自动化学报,2017,43(10):1677-1686,10.基金项目
国家自然科学基金(61573348,61620106003)资助 （61573348,61620106003）
Supported by National Natural Science Foundation of China(61573348,61620106003) （61573348,61620106003）
