Sparse Canonical Correlation Analysis, Overview
Abstract:
This talk gives a brief introduction to Canonical Correlation Analysis (CCA), which is a standard multivariate analysis tool that is used to find linear combinations of two sets of features with the maximum correlation. Its use for the modern high-dimensional data sets is challenging as usually it is of interest to select only a small subset of variables. Consequently, several methods for sparse CCA have been proposed in the literature. I will briefly describe two of these methods (Witten & Tibshirani, 2009 and Chen et al., 2013) and highlight some of their advantages and disadvantages. Time permitting, I will discuss a new methodology for sparse CCA that has the potential of overcoming these drawbacks, which is work in progress.