Univ. Heidelberg
Statistics Group   Institute for Mathematics   Faculty of Mathematics and Computer Science   University Heidelberg
Ruprecht-Karls-Universität Heidelberg Institute for Mathematics Statistics of inverse problems Research Group
german english french


Publications
Cooperations
Research projects
Events
Teaching
Completed theses
People
Contact

Last edited on
Oct 17, 2024 by JJ.
Jan JOHANNES Apr 26,2019 Theses
Thesis:
Bachelor in Mathematics

Author:
Bianca Neubert

Title:
Minimax classification with the nearest neighbor rule

Supervisor:
Jan JOHANNES

Abstract:
In this thesis we consider binary classification with the Nearest Neighbor Rule. We use the minimax approach to evaluate its prediction ability in the finite dimensional case. Deriving the same rate both as an lower bound for the minimax risk and as an upper bound for the maximum risk of the Nearest Neighbor Rule, we can conclude uniform consistency. A short simulation study at the end of the thesis illustrates the discussion.

References:
Gadat, Klein and Marteau. Classification with the nearest neighbor rule in general finite dimensional spaces: necessary and sufficient conditions., Technical report, arXiv:1411.0894, 2014.