Scalable interpretable learning for multi-response error-in-variables regression

JOURNAL OF MULTIVARIATE ANALYSIS

卷:179

Article

Wu, Jie^1,2  Zheng, Zemin^1,2  Li, Yang^1,2  Zhang, Yi^1,2 

[1] Univ Sci & Technol China, Sch Management, Hefei, Peoples R China

[2] Univ Sci & Technol China, Sch Data Sci, Hefei, Peoples R China

关键词: Large-scale association analysis;    Measurement errors;    Scalability;    Sequential pursuit;    Latent factors;   

DOI  :  10.1016/j.jmva.2020.104644

来源: Elsevier

【 摘 要 】

Corrupted data sets containing noisy or missing observations are prevalent in various contemporary applications such as economics, finance and bioinformatics. Despite the recent methodological and algorithmic advances in high-dimensional multi-response regression, how to achieve scalable and interpretable estimation under contaminated covariates is unclear. In this paper, we develop a new methodology called convex conditioned sequential sparse learning (COSS) for error-in-variables multi-response regression under both additive measurement errors and random missing data. It combines the strengths of the recently developed sequential sparse factor regression and the nearest positive semi-definite matrix projection, thus enjoying stepwise convexity and scalability in large-scale association analyses. Comprehensive theoretical guarantees are provided and we demonstrate the effectiveness of the proposed methodology through numerical studies. (C) 2020 Elsevier Inc. All rights reserved.

【 授权许可】

Free