conftrace_

2014 NeurIPS NeurIPS 2014

Optimal rates for k-NN density and mode estimation

Abstract

We present two related contributions of independent interest: (1) high-probability finite sample rates for $k$-NN density estimation, and (2) practical mode estimators -- based on $k$-NN -- which attain minimax-optimal rates under surprisingly general distributional conditions.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

📈 Trend Setter - Density Estimation

🐣 Hot Topic Early Bird - k-nearest neighbor

Authors

Sanjoy Dasgupta, Samory Kpotufe

Topics

Machine Learning > Core Methods > Clustering Machine Learning > Core Methods > Regression Machine Learning > Optimization & Theory > Statistical Learning Machine Learning > Optimization & Theory > Theory Mathematics & Optimization > Statistics Machine Learning > Core Methods > Density Estimation

Keywords

density estimation mode estimation nonparametric statistics k-nearest neighbor minimax rate minimax optimal rate k-nn estimation k-nn density estimation finite sample rate

More from NeurIPS 2014

All NeurIPS 2014 papers →

Robust Tensor Decomposition with Gross Corruption

Structure Regularization for Structured Prediction

Automatic Discovery of Cognitive Skills to Improve the Prediction of Student Learning

Optimization Methods for Sparse Pseudo-Likelihood Graphical Model Selection

Mind the Nuisance: Gaussian Process Classification using Privileged Noise

Accelerated Mini-batch Randomized Block Coordinate Descent Method