How to extract important features and observations in large scale multivariate analyses – Constraining the Singular Value Decomposition.

EVENT : C3BI Seminars

Main speaker : Herve Abdi, from Professor, School of Behavioral and Brain Sciences, The University of Texas, Dallas
Date : 31-05-2018 at 02:00 pm
Location : Auditorium Francois Jacob – BIME (26) ,Institut Pasteur, Paris

The Singular Value Decomposition (SVD)—the core of most popular multivariate methods—analyzes a data table by generating orthogonal components (for the rows) and loadings (for the columns) that, together, extract the important information of a data table. loadings are used to interpret the corresponding components and this interpretation is greatly facilitated when only few variables have large loadings. When this pattern does not hold, several techniques can generate sparse components and loadings but, in most methods, this sparsification is obtained at the cost of orthogonality. Here we propose a new approach for the SVD that includes sparsity constraints on the columns and rows of a rectangular matrix while keeping the pseudo-singular vectors orthogonal. We illustrate this new approach with a psychometric application, 2D images and gene expression data.

Due to security policy in Institut Pasteur, please register before if you plan to come to this meeting