Benefit of Interpolation in Nearest Neighbor Algorithms

DOI10.1137/21M1437457zbMath1493.62180arXiv2202.11817OpenAlexW2976673394MaRDI QIDQ5089734

Qifan Song, Yue Xing, Guang Cheng

Publication date: 15 July 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2202.11817

zbMATH Keywords

interpolationclassificationregressionregret analysisdouble-descentnearest neighbors algorithm

Mathematics Subject Classification ID

Nonparametric estimation (62G05)

Related Items (2)

Unnamed Item ⋮ Tnn: a transfer learning classifier based on weighted nearest neighbors

Uses Software

• Scikit

Cites Work

• Unnamed Item
• Unnamed Item
• Optimal weighted nearest neighbour classifiers
• Fast learning rates for plug-in classifiers
• Optimal aggregation of classifiers in statistical learning.
• Fat-shattering and the learnability of real-valued functions
• Surprises in high-dimensional ridgeless least squares interpolation
• Local nearest neighbour classification with applications to semi-supervised learning
• Optimal Dual Martingales, Their Analysis, and Application to New Algorithms for Bermudan Products
• Distribution-free exponential error bound for nearest neighbor pattern classification
• 10.1162/153244302760200704
• Two Models of Double Descent for Weak Features
• Benign overfitting in linear regression
• Reconciling modern machine-learning practice and the classical bias–variance trade-off
• Convergence of the nearest neighbor rule

This page was built for publication: Benefit of Interpolation in Nearest Neighbor Algorithms