Permutation estimation and minimax rates of identifiability - École des Ponts ParisTech Access content directly
Journal Articles JMLR Year : 2013

Permutation estimation and minimax rates of identifiability


The problem of matching two sets of features appears in various tasks of computer vision and can be often formalized as a problem of permutation estimation. We address this problem from a statistical point of view and provide a theoretical analysis of the accuracy of several natural estimators. To this end, the notion of the minimax rate of identifiability is introduced and its expression is obtained as a function of the sample size, noise level and dimensionality. We consider the cases of homoscedastic and heteroscedastic noise and carry out, in each case, upper bounds on the identifiability threshold of several estimators. This upper bounds are shown to be unimprovable in the homoscedastic setting. We also discuss the computational aspects of the estimators and provide empirical evidence of their consistency on synthetic data.
Fichier principal
Vignette du fichier
CollierDalalyan_aistats2013.pdf (485.44 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00787916 , version 1 (13-02-2013)


  • HAL Id : hal-00787916 , version 1


Olivier Collier, Arnak S. Dalalyan. Permutation estimation and minimax rates of identifiability. JMLR, 2013, 31, pp.10-19. ⟨hal-00787916⟩
502 View
218 Download


Gmail Facebook X LinkedIn More