English

Detecting null patterns in tensor data

Numerical Analysis 2026-01-27 v3 Data Structures and Algorithms Numerical Analysis

Abstract

This article introduces a class of efficiently computable null patterns for tensor data. The class includes familiar patterns such as block-diagonal decompositions explored in statistics and signal processing, low-rank tensor decompositions, and Tucker decompositions. It also includes a new family of null patterns -- not known to be detectable by current methods -- that can be thought of as continuous decompositions approximating curves and surfaces. We present a general algorithm to detect null patterns in each class using a parameter we call a \textit{chisel} that tunes the search to patterns of a prescribed shape. We also show that the patterns output by the algorithm are essentially unique.

Keywords

Cite

@article{arxiv.2408.17425,
  title  = {Detecting null patterns in tensor data},
  author = {Peter A. Brooksbank and Martin D. Kassabov and James B. Wilson},
  journal= {arXiv preprint arXiv:2408.17425},
  year   = {2026}
}

Comments

22 pages, 11 figures

R2 v1 2026-06-28T18:29:05.376Z