An adaptive multiclass nearest neighbor classifier
From MaRDI portal
Publication:5110210
DOI10.1051/ps/2019021zbMath1440.62250arXiv1804.02756OpenAlexW3106082791MaRDI QIDQ5110210
Nikita Puchkin, Vladimir Spokoiny
Publication date: 18 May 2020
Published in: ESAIM: Probability and Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1804.02756
Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30)
Related Items
Minimax adaptive estimation in manifold inference, Towards convergence rate analysis of random forests for classification, Unnamed Item
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Classification in general finite dimensional spaces with the \(k\)-nearest neighbor rule
- The multi-armed bandit problem with covariates
- Kullback-Leibler aggregation and misspecified generalized linear models
- Deviation optimal learning using greedy \(Q\)-aggregation
- Optimal weighted nearest neighbour classifiers
- Parameter tuning in pointwise adaptation using a propagation approach
- Learning by mirror averaging
- Fast learning rates for plug-in classifiers
- Class prediction by nearest shrunken centroids, with applications to DNA microarrays.
- Smooth discrimination analysis
- Local nearest neighbour classification with applications to semi-supervised learning
- Optimal exponential bounds for aggregation of estimators for the Kullback-Leibler loss
- Recursive aggregation of estimators by the mirror descent algorithm with averaging
- Empirical risk minimization is optimal for the convex aggregation problem
- Optimal learning with \textit{Q}-aggregation
- Spatial aggregation of local likelihood estimates with applications to classification
- Optimal rates of aggregation in classification under low noise assumption
- 10.1162/15324430152733133
- Learning from Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers
- 10.1162/15324430260185628
- Learning Theory and Kernel Machines
- Sparse estimation by exponential weighting