Saved in:
Bibliographic Details
Main Authors: Berenfeld, Clément, Carpentier, Alexandra, Verzelen, Nicolas
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.10004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913947294105600
author Berenfeld, Clément
Carpentier, Alexandra
Verzelen, Nicolas
author_facet Berenfeld, Clément
Carpentier, Alexandra
Verzelen, Nicolas
contents In this paper, we consider the problem of seriation of a permuted structured matrix based on noisy observations. The entries of the matrix relate to an expected quantification of interaction between two objects: the higher the value, the closer the objects. A popular structured class for modelling such matrices is the permuted Robinson class, namely the set of matrices whose coefficients are decreasing away from its diagonal, up to a permutation of its lines and columns. We consider in this paper two submodels of Robinson matrices: the Toeplitz model, and the latent position model. We provide a computational lower bound based on the low-degree paradigm, which hints that there is a statistical-computational gap for seriation when measuring the error based on the Frobenius norm. We also provide a simple and polynomial-time algorithm that achives this lower bound. Along the way, we also characterize the information-theory optimal risk thereby giving evidence for the extent of the computation/information gap for this problem.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10004
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Seriation of Toeplitz and latent position matrices: optimal rates and computational trade-offs
Berenfeld, Clément
Carpentier, Alexandra
Verzelen, Nicolas
Statistics Theory
In this paper, we consider the problem of seriation of a permuted structured matrix based on noisy observations. The entries of the matrix relate to an expected quantification of interaction between two objects: the higher the value, the closer the objects. A popular structured class for modelling such matrices is the permuted Robinson class, namely the set of matrices whose coefficients are decreasing away from its diagonal, up to a permutation of its lines and columns. We consider in this paper two submodels of Robinson matrices: the Toeplitz model, and the latent position model. We provide a computational lower bound based on the low-degree paradigm, which hints that there is a statistical-computational gap for seriation when measuring the error based on the Frobenius norm. We also provide a simple and polynomial-time algorithm that achives this lower bound. Along the way, we also characterize the information-theory optimal risk thereby giving evidence for the extent of the computation/information gap for this problem.
title Seriation of Toeplitz and latent position matrices: optimal rates and computational trade-offs
topic Statistics Theory
url https://arxiv.org/abs/2408.10004