logo
banner

Journals & Publications

Journals Publications Papers

Papers

Parameter Identifiability in Statistical Machine Learning: A Review
Jul 24, 2017Author:
PrintText Size A A

Title: Parameter Identifiability in Statistical Machine Learning: A Review

 Authors: Ran, ZY; Hu, BG

 Author Full Names: Ran, Zhi-Yong; Hu, Bao-Gang

 Source: NEURAL COMPUTATION, 29 (5):1151-1203; 10.1162/NECO_a_00947 MAY 2017 

Language: English

 Abstract: 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.

 ISSN: 0899-7667

 eISSN: 1530-888X

 IDS Number: ES6SK

 Unique ID: WOS:000399679500001

 PubMed ID: 28181880

*Click Here to View Full Record