Saved in:
Bibliographic Details
Main Author: Tygert, Mark
Format: Preprint
Published: 2017
Subjects:
Online Access:https://arxiv.org/abs/1710.04238
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911828991279104
author Tygert, Mark
author_facet Tygert, Mark
contents Linear least-squares regression with a "design" matrix A approximates a given matrix B via minimization of the spectral- or Frobenius-norm discrepancy ||AX-B|| over every conformingly sized matrix X. Another popular approximation is low-rank approximation via principal component analysis (PCA) -- which is essentially singular value decomposition (SVD) -- or interpolative decomposition (ID). Classically, PCA/SVD and ID operate solely with the matrix B being approximated, not supervised by any auxiliary matrix A. However, linear least-squares regression models can inform the ID, yielding regression-aware ID. As a bonus, this provides an interpretation as regression-aware PCA for a kind of canonical correlation analysis between A and B. The regression-aware decompositions effectively enable supervision to inform classical dimensionality reduction, which classically has been totally unsupervised. The regression-aware decompositions reveal the structure inherent in B that is relevant to regression against A.
format Preprint
id arxiv_https___arxiv_org_abs_1710_04238
institution arXiv
publishDate 2017
record_format arxiv
spellingShingle Regression-aware decompositions
Tygert, Mark
Methodology
Machine Learning
Numerical Analysis
Linear least-squares regression with a "design" matrix A approximates a given matrix B via minimization of the spectral- or Frobenius-norm discrepancy ||AX-B|| over every conformingly sized matrix X. Another popular approximation is low-rank approximation via principal component analysis (PCA) -- which is essentially singular value decomposition (SVD) -- or interpolative decomposition (ID). Classically, PCA/SVD and ID operate solely with the matrix B being approximated, not supervised by any auxiliary matrix A. However, linear least-squares regression models can inform the ID, yielding regression-aware ID. As a bonus, this provides an interpretation as regression-aware PCA for a kind of canonical correlation analysis between A and B. The regression-aware decompositions effectively enable supervision to inform classical dimensionality reduction, which classically has been totally unsupervised. The regression-aware decompositions reveal the structure inherent in B that is relevant to regression against A.
title Regression-aware decompositions
topic Methodology
Machine Learning
Numerical Analysis
url https://arxiv.org/abs/1710.04238