Saved in:
Bibliographic Details
Main Authors: Cai, T. Tony, Chen, Ran, Zhu, Yuancheng
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.00164
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913259361140736
author Cai, T. Tony
Chen, Ran
Zhu, Yuancheng
author_facet Cai, T. Tony
Chen, Ran
Zhu, Yuancheng
contents Optimal estimation and inference for both the minimizer and minimum of a convex regression function under the white noise and nonparametric regression models are studied in a nonasymptotic local minimax framework, where the performance of a procedure is evaluated at individual functions. Fully adaptive and computationally efficient algorithms are proposed and sharp minimax lower bounds are given for both the estimation accuracy and expected length of confidence intervals for the minimizer and minimum. The nonasymptotic local minimax framework brings out new phenomena in simultaneous estimation and inference for the minimizer and minimum. We establish a novel uncertainty principle that provides a fundamental limit on how well the minimizer and minimum can be estimated simultaneously for any convex regression function. A similar result holds for the expected length of the confidence intervals for the minimizer and minimum.
format Preprint
id arxiv_https___arxiv_org_abs_2305_00164
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Estimation and inference for minimizer and minimum of convex functions: optimality, adaptivity and uncertainty principles
Cai, T. Tony
Chen, Ran
Zhu, Yuancheng
Statistics Theory
Methodology
Optimal estimation and inference for both the minimizer and minimum of a convex regression function under the white noise and nonparametric regression models are studied in a nonasymptotic local minimax framework, where the performance of a procedure is evaluated at individual functions. Fully adaptive and computationally efficient algorithms are proposed and sharp minimax lower bounds are given for both the estimation accuracy and expected length of confidence intervals for the minimizer and minimum. The nonasymptotic local minimax framework brings out new phenomena in simultaneous estimation and inference for the minimizer and minimum. We establish a novel uncertainty principle that provides a fundamental limit on how well the minimizer and minimum can be estimated simultaneously for any convex regression function. A similar result holds for the expected length of the confidence intervals for the minimizer and minimum.
title Estimation and inference for minimizer and minimum of convex functions: optimality, adaptivity and uncertainty principles
topic Statistics Theory
Methodology
url https://arxiv.org/abs/2305.00164