Weighted EMPCA: Weighted Expectation Maximization Principal Component Analysis

Discussion topics for individual codes
Post Reply
Ada Coda
ASCL Robot
Posts: 1814
Joined: Thu May 08, 2014 5:37 am

Weighted EMPCA: Weighted Expectation Maximization Principal Component Analysis

Post by Ada Coda » Wed Sep 28, 2016 8:31 am

Weighted EMPCA: Weighted Expectation Maximization Principal Component Analysis

Abstract: Weighted EMPCA performs principal component analysis (PCA) on noisy datasets with missing values. Estimates of the measurement error are used to weight the input data such that the resulting eigenvectors, when compared to classic PCA, are more sensitive to the true underlying signal variations rather than being pulled by heteroskedastic measurement noise. Missing data are simply limiting cases of weight = 0. The underlying algorithm is a noise weighted expectation maximization (EM) PCA, which has additional benefits of implementation speed and flexibility for smoothing eigenvectors to reduce the noise contribution.

Credit: Bailey, Stephen

Site: https://github.com/sbailey/empca
https://ui.adsabs.harvard.edu/abs/2012PASP..124.1015B

Bibcode: 2016ascl.soft09007B

Preferred citation method: https://ui.adsabs.harvard.edu/abs/2012PASP..124.1015B, and optionally an acknowledgement such as This work uses the Weighted EMPCA code by Stephen Bailey, available at https://github.com/sbailey/empca/

ID: ascl:1609.007
Last edited by Ada Coda on Thu Nov 19, 2020 4:48 pm, edited 1 time in total.
Reason: Updated code entry.

Post Reply