Uniform convergence and rate adaptive estimation of convex functions via constrained optimization

DOI10.1137/120887837zbMATH Open1280.41008arXiv1205.0023OpenAlexW2028396654MaRDI QIDQ2862446FDOQ2862446

Authors: Jinglai Shen, Xiao Wang 

Publication date: 15 November 2013

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Abstract: This paper addresses the problem of estimating a convex regression function under both the sup-norm risk and the pointwise risk using B-splines. The presence of the convex constraint complicates various issues in asymptotic analysis, particularly uniform convergence analysis. To overcome this difficulty, we establish the uniform Lipschitz property of optimal spline coefficients in the $el{l}_{i}nfty$-norm by exploiting piecewise linear and polyhedral theory. Based upon this property, it is shown that this estimator attains optimal rates of convergence on the entire interval of interest over the H"older class under both the risks. In addition, adaptive estimates are constructed under both the sup-norm risk and the pointwise risk when the exponent of the H"older class is between one and two. These estimates achieve a maximal risk within a constant factor of the minimax risk over the H"older class.

Full work available at URL: https://arxiv.org/abs/1205.0023

Recommendations

• Estimation of monotone functions via \(P\)-splines: a constrained dynamical optimization approach
• Convergence rates for constrained regression splines
• On convergence rates of convex regression in multiple dimensions
• On uniform consistent estimators for convex regression
• Publication:4728775

zbMATH Keywords

constrained optimizationconvex regressionB-splinesadaptive estimationasymptotic analysisminimax theoryshape restricted nonparametric estimation

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Spline approximation (41A15)

Cited In (9)

• On uniform consistent estimators for convex regression
• Uniform convergence rates for wavelet curve estimation in sup-norm loss
• A two stage \(k\)-monotone B-spline regression estimator: uniform Lipschitz property and optimal convergence rate
• Nonparametric adaptive Bayesian regression using priors with tractable normalizing constants and under qualitative assumptions
• Global risk bounds and adaptation in univariate convex regression
• Nonparametric estimation and inference under shape restrictions
• Estimation of monotone functions via \(P\)-splines: a constrained dynamical optimization approach
• Automatic identification of curve shapes with applications to ultrasonic vocalization
• Partial conditioning for inference of many-normal-means with Hölder constraints

This page was built for publication: Uniform convergence and rate adaptive estimation of convex functions via constrained optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2862446)