Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Noisy classification with boundary assumptions

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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00843776
Contributor : Sébastien Loustau <>
Submitted on : Friday, July 12, 2013 - 10:24:45 AM
Last modification on : Monday, March 9, 2020 - 6:16:02 PM
Document(s) archivé(s) le : Sunday, October 13, 2013 - 4:25:09 AM

Files

BFfinal_Juillet.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00843776, version 1
  • ARXIV : 1307.3369

Citation

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

Share

Metrics

Record views

442

Files downloads

260