Journal article
Fitting sparse linear models under the sufficient and necessary condition for model identification
Statistics & probability letters, Vol.168, p.108925
01/2021
DOI: 10.1016/j.spl.2020.108925
Abstract
We propose an enhanced support detection and root finding approach (ESDAR) to variable selection in sparse linear models. ESDAR is motivated from the KKT conditions for the ℓ0 penalized regression. In ESDAR, we introduce a step size to balance the primal and dual variables in determining the support of the solution. We establish a sharp oracle error bound and an oracle support recovery property for the solution sequence generated by ESDAR under the weakest possible condition on the design matrix that is sufficient and necessary for the model to be identifiable. The conditions for the oracle results we obtained are weaker than those for Lasso and concave selection methods including SCAD and MCP in the literature.
Details
- Title: Subtitle
- Fitting sparse linear models under the sufficient and necessary condition for model identification
- Creators
- Jian Huang - University of IowaYuling Jiao - Wuhan UniversityLican Kang - Wuhan UniversityYanyan Liu - Wuhan University
- Resource Type
- Journal article
- Publication Details
- Statistics & probability letters, Vol.168, p.108925
- Publisher
- Elsevier B.V
- DOI
- 10.1016/j.spl.2020.108925
- ISSN
- 0167-7152
- eISSN
- 1879-2103
- Grant note
- DOI: 10.13039/501100001809, name: National Natural Science Foundation of China; DOI: 10.13039/100000001, name: National Science Foundation
- Language
- English
- Date published
- 01/2021
- Academic Unit
- Statistics and Actuarial Science
- Record Identifier
- 9984257595102771
Metrics
11 Record Views