DeepAI AI Chat
Log In Sign Up

Sparse Principal Component Analysis via Variable Projection

by   N. Benjamin Erichson, et al.
berkeley college

Sparse principal component analysis (SPCA) has emerged as a powerful technique for modern data analysis. We discuss a robust and scalable algorithm for computing sparse principal component analysis. Specifically, we model SPCA as a matrix factorization problem with orthogonality constraints, and develop specialized optimization algorithms that partially minimize a subset of the variables (variable projection). The framework incorporates a wide variety of sparsity-inducing regularizers for SPCA. We also extend the variable projection approach to robust SPCA, for any robust loss that can be expressed as the Moreau envelope of a simple function, with the canonical example of the Huber loss. Finally, randomized methods for linear algebra are used to extend the approach to the large-scale (big data) setting. The proposed algorithms are demonstrated using both synthetic and real world data.


page 8

page 9


A robust approach for principal component analyisis

In this paper we analyze different ways of performing principal componen...

High-Dimensional Inference with the generalized Hopfield Model: Principal Component Analysis and Corrections

We consider the problem of inferring the interactions between a set of N...

A Study on a User-Controlled Radial Tour for Variable Importance in High-Dimensional Data

Principal component analysis is a long-standing go-to method for explori...

Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms

The goal of this paper is to revisit Kernel Principal Component Analysis...

Coreset Construction via Randomized Matrix Multiplication

Coresets are small sets of points that approximate the properties of a l...

Information Projection and Approximate Inference for Structured Sparse Variables

Approximate inference via information projection has been recently intro...

Randomized Nonlinear Component Analysis

Classical methods such as Principal Component Analysis (PCA) and Canonic...

Code Repositories


Sparse Principal Component Analysis (SPCA) using Variable Projection

view repo