Noisy classification with boundary assumptions - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Noisy classification with boundary assumptions

(1) , (2)
1
2

Abstract

We address the problem of classification when data are collected from two samples with measurement errors. This problem turns to be an inverse problem and requires a specific treatment. In this context, we investigate the minimax rates of convergence using both a margin assumption, and a smoothness condition on the boundary of the set associated to the Bayes classifier. We establish lower and upper bounds (based on a deconvolution classifier) on these rates.
Fichier principal
Vignette du fichier
BFfinal_Juillet.pdf (284.25 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00843776 , version 1 (12-07-2013)

Identifiers

Cite

Sébastien Loustau, Clément Marteau. Noisy classification with boundary assumptions. 2013. ⟨hal-00843776⟩
282 View
180 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More