Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dash, Anirudh, Siripuram, Aditya
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.07649
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914963863371776
author Dash, Anirudh
Siripuram, Aditya
author_facet Dash, Anirudh
Siripuram, Aditya
contents Motivated by orthogonal dictionary learning problems, we propose a novel method for matrix factorization, where the data matrix $\mathbf{Y}$ is a product of a Householder matrix $\mathbf{H}$ and a binary matrix $\mathbf{X}$. First, we show that the exact recovery of the factors $\mathbf{H}$ and $\mathbf{X}$ from $\mathbf{Y}$ is guaranteed with $Ω(1)$ columns in $\mathbf{Y}$ . Next, we show approximate recovery (in the $l\infty$ sense) can be done in polynomial time($O(np)$) with $Ω(\log n)$ columns in $\mathbf{Y}$ . We hope the techniques in this work help in developing alternate algorithms for orthogonal dictionary learning.
format Preprint
id arxiv_https___arxiv_org_abs_2405_07649
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Matrix Factorization Via Householder Reflections
Dash, Anirudh
Siripuram, Aditya
Signal Processing
Machine Learning
Motivated by orthogonal dictionary learning problems, we propose a novel method for matrix factorization, where the data matrix $\mathbf{Y}$ is a product of a Householder matrix $\mathbf{H}$ and a binary matrix $\mathbf{X}$. First, we show that the exact recovery of the factors $\mathbf{H}$ and $\mathbf{X}$ from $\mathbf{Y}$ is guaranteed with $Ω(1)$ columns in $\mathbf{Y}$ . Next, we show approximate recovery (in the $l\infty$ sense) can be done in polynomial time($O(np)$) with $Ω(\log n)$ columns in $\mathbf{Y}$ . We hope the techniques in this work help in developing alternate algorithms for orthogonal dictionary learning.
title Efficient Matrix Factorization Via Householder Reflections
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2405.07649