UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Isotonic regression in general dimensions

Han, Q; Wang, T; Chatterjee, S; Samworth, RJ; (2019) Isotonic regression in general dimensions. Annals of Statistics , 47 (5) pp. 2440-2471. 10.1214/18-AOS1753. Green open access

[img]
Preview
Text
Wang_euclid.aos.1564797853.pdf

Download (370kB) | Preview

Abstract

We study the least squares regression function estimator over the class of real-valued functions on [0,1]d that are increasing in each coordinate. For uniformly bounded signals and with a fixed, cubic lattice design, we establish that the estimator achieves the minimax rate of order n−min{2/(d+2),1/d} in the empirical L2 loss, up to poly-logarithmic factors. Further, we prove a sharp oracle inequality, which reveals in particular that when the true regression function is piecewise constant on k hyperrectangles, the least squares estimator enjoys a faster, adaptive rate of convergence of (k/n)min(1,2/d), again up to poly-logarithmic factors. Previous results are confined to the case d≤2. Finally, we establish corresponding bounds (which are new even in the case d=2) in the more challenging random design setting. There are two surprising features of these results: first, they demonstrate that it is possible for a global empirical risk minimisation procedure to be rate optimal up to poly-logarithmic factors even when the corresponding entropy integral for the function class diverges rapidly; second, they indicate that the adaptation rate for shape-constrained estimators can be strictly worse than the parametric rate.

Type: Article
Title: Isotonic regression in general dimensions
Open access status: An open access version is available from UCL Discovery
DOI: 10.1214/18-AOS1753
Publisher version: https://doi.org/10.1214/18-AOS1753
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/10055413
Downloads since deposit
2Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item