Gadat, Sébastien, Gerchinovitz, Sebastien and Marteau, Clément (2020) Optimal functional supervised classification with separation condition. Bernoulli journal, vol. 26 (n°3). pp. 1797-1831.

This is the latest version of this item.

[thumbnail of wp_tse_904.pdf]
Preview
Text
Download (804kB) | Preview
Identification Number : 10.3150/19-BEJ1170

Abstract

We consider the binary supervised classification problem with the Gaussian functional model introduced in [7]. Taking advantage of the Gaussian structure, we design a natural plug-in classifier and derive a family of upper bounds on its worst-case excess risk over Sobolev spaces. These bounds are parametrized by a separation distance quantifying the difficulty of the problem, and are proved to be optimal (up to logarithmic factors) through matching minimax lower bounds. Using the recent works of [9] and [14] we also derive a logarithmic lower bound showing that the popular k-nearest neighbors classifier is far from optimality in this specific functional setting.

Item Type: Article
Language: English
Date: 2020
Refereed: Yes
Place of Publication: Londres
Subjects: B- ECONOMIE ET FINANCE
Divisions: TSE-R (Toulouse)
Site: UT1
Date Deposited: 01 Oct 2019 13:59
Last Modified: 27 Oct 2021 13:37
OAI Identifier: oai:tse-fr.eu:123580
URI: https://publications.ut-capitole.fr/id/eprint/32803

Available Versions of this Item

View Item

Downloads

Downloads per month over past year