Multivariate and functional robust fusion methods for structured Big Data

JOURNAL OF MULTIVARIATE ANALYSIS

卷:170

Article

Aaron, Catherine¹  Cholaquidis, Alejandro^2,3  Fraiman, Ricardo^2,3,4  Ghattas, Badih⁵ 

[1] Univ Clermont Auvergne, Campus Univ Cezeaux, Aubiere, France

[2] Univ Republica, CABIDA, Montevideo, Uruguay

[3] Univ Republica, Ctr Matemat, Montevideo, Uruguay

[4] Inst Pasteur Montevideo, Montevideo, Uruguay

[5] Aix Marseille Univ, CNRS, Cent Marseille, I2M,UMR 7373, F-13453 Marseille, France

关键词: Big data;    Clustering;    Functional data;    Robustness;   

DOI  :  10.1016/j.jmva.2018.06.012

来源: Elsevier

【 摘 要 】

We address one of the important problems in Big Data, namely how to combine estimators from different subsamples by robust fusion procedures, when we are unable to deal with the whole sample. We propose a general framework based on the classic idea of 'divide and conquer'. In particular we address in some detail the case of a multivariate location and scatter matrix, the covariance operator for functional data, and clustering problems. (C) 2018 Elsevier Inc. All rights reserved.

【 授权许可】

Free