Saved in:
Bibliographic Details
Main Authors: Rossetti, Riccardo, Reeves, Galen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.06749
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908398651441152
author Rossetti, Riccardo
Reeves, Galen
author_facet Rossetti, Riccardo
Reeves, Galen
contents This paper provides a unified framework for analyzing tensor estimation problems that allow for nonlinear observations, heteroskedastic noise, and covariate information. We study a general class of high-dimensional models where each observation depends on the interactions among a finite number of unknown parameters. Our main results provide asymptotically exact formulas for the mutual information (equivalently, the free energy) as well as the minimum mean-squared error in the Bayes-optimal setting. We then apply this framework to derive sharp characterizations of statistical thresholds for two novel scenarios: (1) tensor estimation in heteroskedastic noise that is independent but not identically distributed, and (2) higher-order assignment problems, where the goal is to recover an unknown permutation from tensor-valued observations.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06749
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Statistical Limits for Finite-Rank Tensor Estimation
Rossetti, Riccardo
Reeves, Galen
Information Theory
Statistics Theory
This paper provides a unified framework for analyzing tensor estimation problems that allow for nonlinear observations, heteroskedastic noise, and covariate information. We study a general class of high-dimensional models where each observation depends on the interactions among a finite number of unknown parameters. Our main results provide asymptotically exact formulas for the mutual information (equivalently, the free energy) as well as the minimum mean-squared error in the Bayes-optimal setting. We then apply this framework to derive sharp characterizations of statistical thresholds for two novel scenarios: (1) tensor estimation in heteroskedastic noise that is independent but not identically distributed, and (2) higher-order assignment problems, where the goal is to recover an unknown permutation from tensor-valued observations.
title Statistical Limits for Finite-Rank Tensor Estimation
topic Information Theory
Statistics Theory
url https://arxiv.org/abs/2506.06749