Research Area:  Machine Learning

Abstract:

Coresets have emerged as a powerful tool to summarize data by selecting a small subset of the original observations while retaining most of its information. This approach has led to significant computational speedups but the performance of statistical procedures run on coresets is largely unexplored. In this work, we develop a statistical framework to study coresets and focus on the canonical task of nonparameteric density estimation. Our contributions are twofold. First, we establish the minimax rate of estimation achievable by coreset-based estimators. Second, we show that the practical coreset kernel density estimators are near-minimax optimal over a large class of Holder-smooth densities.

Keywords:  
Coreset
Density Estimation
Deep Learning
Machine Learning

Author(s) Name:  Paxton Turner, Jingbo Liu, Philippe Rigollet

Publisher name:  MLR press

DOI:  10.48550/arXiv.2011.04907

Volume Information:  

Paper Link:   https://proceedings.mlr.press/v130/turner21b.html