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 message-passing methods.
Multivariate Priors and the Linearity of Optimal Bayesian Estimators under Gaussian Noise
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Consider the task of estimating a random vector $X$ from noisy observations $Y = X + Z$, where $Z$ is a standard normal vector, under the $L^p$ fidelity criterion. This work establishes that, for $1 \leq p \leq 2$, the optimal Bayesian estimator is linear and positive definite if and only if the prior distribution on $X$ is a (non-degenerate) multivariate Gaussian. Furthermore, for $p > 2$, it is demonstrated that there are infinitely many priors that can induce such an estimator.
citation-role summary
background 1
citation-polarity summary
fields
cond-mat.dis-nn 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
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 message-passing methods.