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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.dis-nn 1years
2025 1verdicts
CONDITIONAL 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.