English

Rectangular Rotational Invariant Estimator for High-Rank Matrix Estimation

Information Theory 2024-03-08 v1 math.IT

Abstract

We consider estimating a matrix from noisy observations coming from an arbitrary additive bi-rotational invariant perturbation. We propose an estimator which is optimal among the class of rectangular rotational invariant estimators and can be applied irrespective of the prior on the signal. For the particular case of Gaussian noise, we prove the optimality of the proposed estimator, and we find an explicit expression for the MMSE in terms of the limiting singular value distribution of the observation matrix. Moreover, we prove a formula linking the asymptotic mutual information and the limit of a log-spherical integral of rectangular matrices. We also provide numerical checks for our results for general bi-rotational invariant noise, as well as Gaussian noise, which match our theoretical predictions.

Keywords

Cite

@article{arxiv.2403.04615,
  title  = {Rectangular Rotational Invariant Estimator for High-Rank Matrix Estimation},
  author = {Farzad Pourkamali and Nicolas Macris},
  journal= {arXiv preprint arXiv:2403.04615},
  year   = {2024}
}

Comments

arXiv admin note: text overlap with arXiv:2304.12264

R2 v1 2026-06-28T15:12:30.602Z