Canonical Correlation Analysis in high dimensions with structured regularization

11/03/2020
by   Elena Tuzhilina, et al.
0

Canonical Correlation Analysis (CCA) is a technique for measuring the association between two multivariate sets of variables. The Regularized modification of Canonical Correlation Analysis (RCCA) imposing ℓ_2 penalty on the CCA coefficients is widely used in applications while conducting the analysis of high dimensional data. One limitation of such a regularization type is that it ignores the data structure treating all the features equally, which can be ill-suited for some applications. In this paper we introduce several approaches to regularizing CCA that take the underlying data structure into account. In particular, the proposed Group Regularized Canonical Correlation Analysis (GRCCA) is useful when the variables are grouped. We also suggest some tricks that allow to avoid excessive computations while conducting CCA with regularization in high dimensions. We demonstrate the applications of these methods to a small simulation example as well as to a real data example from neuroscience.

READ FULL TEXT

page 18

page 19

page 24

research
06/28/2023

High-Dimensional Canonical Correlation Analysis

This paper studies high-dimensional canonical correlation analysis (CCA)...
research
05/11/2020

Probabilistic Canonical Correlation Analysis for Sparse Count Data

Canonical correlation analysis (CCA) is a classical and important multiv...
research
02/10/2018

Probabilistic Canonical Correlation Analysis: A Whitening Approach

Canonical correlation analysis (CCA) is a classic and widely used statis...
research
12/06/2018

Finding the needle in high-dimensional haystack: A tutorial on canonical correlation analysis

Since the beginning of the 21st century, the size, breadth, and granular...
research
11/20/2020

Robust smoothed canonical correlation analysis for functional data

This paper provides robust estimators for the first canonical correlatio...
research
02/02/2023

Longitudinal Canonical Correlation Analysis

This paper considers canonical correlation analysis for two longitudinal...
research
10/17/2020

Significance testing for canonical correlation analysis in high dimensions

We consider the problem of testing for the presence of linear relationsh...

Please sign up or login with your details

Forgot password? Click here to reset