REVIEW 2 cited by
Rectangular Rotational Invariant Estimator for General Additive Noise Matrices
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We propose a rectangular rotational invariant estimator to recover a real matrix from noisy matrix observations coming from an arbitrary additive rotational invariant perturbation, in the large dimension limit. Using the Bayes-optimality of this estimator, we derive the asymptotic minimum mean squared error (MMSE). For the particular case of Gaussian noise, 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 log-spherical integral of rectangular matrices. We also provide numerical checks for our results, which match our theoretical predictions and known Bayesian inference results.
Forward citations
Cited by 2 Pith papers
-
BBP Phase Transition for an Extensive Number of Outliers
For a rectangular random matrix with an extensive number of degenerate signal singular values, the spectrum obeys a quartic equation that gives a generalized BBP phase diagram and a 1/3-power scaling law.
-
Some observations on the ambivalent role of symmetries in Bayesian inference problems
Unobservable symmetries in Bayesian inference require quotienting the error metric, and for extensive-rank matrix factorization this leads to a three-level optimization problem that may be inaccessible to local messag...
Discussion (0). Continue with ORCID to comment.