Exploring the Limitations of Structured Orthogonal Dictionary Learning
Abstract
This work is motivated by recent applications of structured dictionary learning, in particular when the dictionary is assumed to be the product of a few Householder atoms. We investigate the following two problems: 1) How do we approximate an orthogonal matrix with a product of a specified number of Householder matrices, and 2) How many samples are required to learn a structured (Householder) dictionary from data? For 1) we discuss an algorithm that decomposes as a product of a specified number of Householder matrices. We see that the algorithm outputs the decomposition when it exists, and give bounds on the approximation error of the algorithm when such a decomposition does not exist. For 2) given data , we show that when assuming a binary coefficient matrix , the structured (Householder) dictionary learning problem can be solved with just samples (columns) in .
Cite
@article{arxiv.2501.15094,
title = {Exploring the Limitations of Structured Orthogonal Dictionary Learning},
author = {Anirudh Dash and Aditya Siripuram},
journal= {arXiv preprint arXiv:2501.15094},
year = {2025}
}
Comments
14 pages, 6 figures. arXiv admin note: text overlap with arXiv:2405.07649