Publications
Detailed Information
Comparative study of computational algorithms for the Lasso under high-dimensional, highly correlated data : 고차원의 상관계수가 높은 자료에서의 라쏘의 계산 알고리즘들의 비교 연구
Cited 0 time in
Web of Science
Cited 0 time in Scopus
- Authors
- Advisor
- 임요한
- Major
- 자연과학대학 통계학과
- Issue Date
- 2016-02
- Publisher
- 서울대학교 대학원
- Keywords
- Lasso
- Description
- 학위논문 (석사)-- 서울대학교 대학원 : 통계학과, 2016. 2. 임요한.
- Abstract
- Variable selection is important in high-dime\-nsional data analysis. The Lasso regression is useful since it possesses sparsity, soft-decision rule, and computational efficiency.
However, since the Lasso penalized likelihood contains a nondifferentiable term, standard optimization tools cannot be applied. Many computation algorithms to optimize this Lasso penalized likelihood function in high-dimensional settings have been proposed. To name a few, coordinate descent (CD) algorithm, majorization-minimization using local quadratic approximation, fast iterative shrinkage thresholding algorithm (FISTA) and alternating direction methods of multiplier (ADMM).
In this paper, we undertake a comparative study that analyzes relative merits of these algorithms. We are especially concerned with numerical sensitivity to the correlation between the covariates. We conduct a simulation study considering factors
that affect the condition number of covariance matrix of the covariates, as well as the level of penalization. We apply the algorithms to cancer biomarker discovery, and compare convergence speed and stability.
- Language
- English
- Files in This Item:
- Appears in Collections:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.