Umeyama algorithm achieves exact recovery of latent permutation π* in correlated Gaussian geometric models for σ = o(d^{-3}n^{-2/d}) and almost exact for σ = o(d^{-3}n^{-1/d}) when d = O(log n).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Umeyama algorithm for matching correlated Gaussian geometric models in the low-dimensional regime
Umeyama algorithm achieves exact recovery of latent permutation π* in correlated Gaussian geometric models for σ = o(d^{-3}n^{-2/d}) and almost exact for σ = o(d^{-3}n^{-1/d}) when d = O(log n).