This is not the latest version of this item. The latest version can be found here.
Sparse PCA from sparse linear regression
Name
8291-sparse-pca-from-sparse-linear-regression.pdf
Description
Published version
Size
726.49 KB
Format
Adobe PDF
Checksum (MD5)
3294096a07b77ce917edb518a3a06716
Author(s)
Bresler, Guy
Park, Sung Min
Persu, Madalina
Date Issued
2018
Citation
Bresler, Guy, Park, Sung Min and Persu, Madalina. 2018. "Sparse PCA from sparse linear regression."
Version
Final published version
Abstract
© 2018 Curran Associates Inc.All rights reserved. Sparse Principal Component Analysis (SPCA) and Sparse Linear Regression (SLR) have a wide range of applications and have attracted a tremendous amount of attention in the last two decades as canonical examples of statistical problems in high dimension. A variety of algorithms have been proposed for both SPCA and SLR, but an explicit connection between the two had not been made. We show how to efficiently transform a black-box solver for SLR into an algorithm for SPCA: assuming the SLR solver satisfies prediction error guarantees achieved by existing efficient algorithms such as those based on the Lasso, the SPCA algorithm derived from it achieves near state of the art guarantees for testing and for support recovery for the single spiked covariance model as obtained by the current best polynomial-time algorithms. Our reduction not only highlights the inherent similarity between the two problems, but also, from a practical standpoint, allows one to obtain a collection of algorithms for SPCA directly from known algorithms for SLR. We provide experimental results on simulated data comparing our proposed framework to other algorithms for SPCA.
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/8291-sparse-pca-from-sparse-linear-regression
