Skip to content
ePCA implementation, as described in "ePCA: High Dimensional Exponential Family PCA"
MATLAB
Branch: master
Clone or download
Latest commit 7d39773 Aug 1, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
experiments check Jan 15, 2017
software added files Nov 15, 2016
.gitignore Create .gitignore Nov 20, 2016
LICENSE.txt Create LICENSE.txt Nov 20, 2016
README.md Update README.md Aug 1, 2019

README.md

ePCA

Software implementation for ePCA and denoising as described in the paper:

  • Lydia T. Liu, Edgar Dobriban and Amit Singer. ePCA: High Dimensional Exponential Family PCA. Ann. Appl. Stat., Volume 12, Number 4 (2018), 2121-2150.

The manuscript is also available on arXiv.

Contents

  • software/ : software for applying ePCA on one's own datasets. In particular, exp_fam_pca.m implements ePCA and wiener_filter.m implements the generalized wiener filter (or EBLP) for denoising, as introduced in the aforementioned paper.
  • experiments/ : scripts for reproducing experimental results in the aforementioned paper. Large datasets are excluded.

Requirements

MATLAB. No other downloads are required.

Acknowledgements

This implementation uses standard_spiked_forward.m from EigenEdge.

You can’t perform that action at this time.