Adaptive nonparametric regression with the K-nearest neighbour fused Lasso

DOI10.1093/BIOMET/ASZ071MaRDI QIDQ5113012zbMATH OpenOpenAlexWikidataFDO

Authors Oscar-Hernan Madrid-Padilla, James Sharpnack, Yanzhen Chen, Daniela M. Witten

Publication date 9 June 2020

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1807.11641

zbMATH Keywords

fused Lassolocal adaptivitymanifold adaptivitynonparametric regressionregular grid of design pointstotal variation

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Ridge regression; shrinkage estimators (Lasso) (62J07) Statistical block designs (62K10)

Abstract: The fused lasso, also known as total-variation denoising, is a locally-adaptive function estimator over a regular grid of design points. In this paper, we extend the fused lasso to settings in which the points do not occur on a regular grid, leading to an approach for non-parametric regression. This approach, which we call the $K$-nearest neighbors ($K$-NN) fused lasso, involves (i) computing the $K$-NN graph of the design points; and (ii) performing the fused lasso over this $K$-NN graph. We show that this procedure has a number of theoretical advantages over competing approaches: specifically, it inherits local adaptivity from its connection to the fused lasso, and it inherits manifold adaptivity from its connection to the $K$-NN approach. We show that excellent results are obtained in a simulation study and on an application to flu data. For completeness, we also study an estimator that makes use of an $epsilon$-graph rather than a $K$-NN graph, and contrast this with the $K$-NN fused lasso.

Recommendations

• k-Nearest Neighbour method in functional nonparametric regression
• Sparsity and Smoothness Via the Fused Lasso
• scientific article; zbMATH DE number 1347887
• Properties and refinements of the fused Lasso
• Adaptive basis expansion via \(\ell _1\) trend filtering

Cited in

(15)

• The DFS fused Lasso: linear-time denoising over general graphs
• Adaptive regularization for Lasso models in the context of nonstationary data streams
• scientific article; zbMATH DE number 7370628 (Why is no real title available?)
• Intrinsic dimension adaptive partitioning for kernel methods
• Nonparametric regression with adaptive truncation via a convex hierarchical penalty
• Fusion learning of functional linear regression with application to genotype-by-environment interaction studies
• Graphon estimation via nearest‐neighbour algorithm and two‐dimensional fused‐lasso denoising
• Biconvex Clustering
• Varying-coefficients for regional quantile via KNN-based LASSO with applications to health outcome study
• Multivariate trend filtering for lattice data
• Learning conditional distributions on continuous spaces
• Data-driven segmentation of observation-level logistic regression models
• Reduced varying coefficient models for regional quantile regression with multiple responses
• High-dimensional partial linear model with trend filtering
• Subgroup identification and membership prediction

This page was built for publication: Adaptive nonparametric regression with the \(K\)-nearest neighbour fused Lasso

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5113012)