English

Exploring the Limitations of Structured Orthogonal Dictionary Learning

Signal Processing 2025-04-21 v2

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 V\mathbf{V} 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 V\mathbf{V} 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 Y=HX\mathbf{Y}=\mathbf{HX}, we show that when assuming a binary coefficient matrix X\mathbf{X}, the structured (Householder) dictionary learning problem can be solved with just 22 samples (columns) in Y\mathbf{Y}.

Keywords

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

R2 v1 2026-06-28T21:17:20.529Z