A0343
Title: Scalable multiclass high-dimensional linear discriminant analysis via the randomized Kaczmarz method
Authors: Jocelyn Chi - University of Colorado Boulder (United States) [presenting]
Abstract: Fisher's linear discriminant analysis (LDA) is a foundational method of dimension reduction for classification that has been useful in a wide range of applications. The goal is to identify an optimal subspace to project the observations onto that simultaneously maximizes between-group variation while minimizing within-group differences. The solution is straightforward when the number of observations is greater than the number of features, but difficulties arise in the high dimensional setting, where there are more features than there are observations. Many works have proposed solutions for the high dimensional setting and frequently involve additional assumptions or tuning parameters. A fast and simple iterative algorithm is proposed for high-dimensional multiclass LDA on large data that is free from these additional requirements and that comes with some guarantees. The algorithm is demonstrated on real data, and some results are highlighted.
