Optimal Recovery Meets Minimax Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: DeVore, Ronald, Nowak, Robert D., Parhi, Rahul, Petrova, Guergana, Siegel, Jonathan W.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916765263462400
author DeVore, Ronald
Nowak, Robert D.
Parhi, Rahul
Petrova, Guergana
Siegel, Jonathan W.
author_facet DeVore, Ronald
Nowak, Robert D.
Parhi, Rahul
Petrova, Guergana
Siegel, Jonathan W.
contents A fundamental problem in statistics and machine learning is to estimate a function $f$ from possibly noisy observations of its point samples. The goal is to design a numerical algorithm to construct an approximation $\hat f$ to $f$ in a prescribed norm that asymptotically achieves the best possible error (as a function of the number $m$ of observations and the variance $σ^2$ of the noise). This problem has received considerable attention in both nonparametric statistics (noisy observations) and optimal recovery (noiseless observations). Quantitative bounds require assumptions on $f$, known as model class assumptions. Classical results assume that $f$ is in the unit ball of a Besov space. In nonparametric statistics, the best possible performance of an algorithm for finding $\hat f$ is known as the minimax rate and has been studied in this setting under the assumption that the noise is Gaussian. In optimal recovery, the best possible performance of an algorithm is known as the optimal recovery rate and has also been determined in this setting. While one would expect that the minimax rate recovers the optimal recovery rate when the noise level $σ$ tends to zero, it turns out that the current results on minimax rates do not carefully determine the dependence on $σ$ and the limit cannot be taken. This paper handles this issue and determines the noise-level-aware (NLA) minimax rates for Besov classes when error is measured in an $L_q$-norm with matching upper and lower bounds. The end result is a reconciliation between minimax rates and optimal recovery rates. The NLA minimax rate continuously depends on the noise level and recovers the optimal recovery rate when $σ$ tends to zero.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17671
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimal Recovery Meets Minimax Estimation
DeVore, Ronald
Nowak, Robert D.
Parhi, Rahul
Petrova, Guergana
Siegel, Jonathan W.
Statistics Theory
Numerical Analysis
Machine Learning
A fundamental problem in statistics and machine learning is to estimate a function $f$ from possibly noisy observations of its point samples. The goal is to design a numerical algorithm to construct an approximation $\hat f$ to $f$ in a prescribed norm that asymptotically achieves the best possible error (as a function of the number $m$ of observations and the variance $σ^2$ of the noise). This problem has received considerable attention in both nonparametric statistics (noisy observations) and optimal recovery (noiseless observations). Quantitative bounds require assumptions on $f$, known as model class assumptions. Classical results assume that $f$ is in the unit ball of a Besov space. In nonparametric statistics, the best possible performance of an algorithm for finding $\hat f$ is known as the minimax rate and has been studied in this setting under the assumption that the noise is Gaussian. In optimal recovery, the best possible performance of an algorithm is known as the optimal recovery rate and has also been determined in this setting. While one would expect that the minimax rate recovers the optimal recovery rate when the noise level $σ$ tends to zero, it turns out that the current results on minimax rates do not carefully determine the dependence on $σ$ and the limit cannot be taken. This paper handles this issue and determines the noise-level-aware (NLA) minimax rates for Besov classes when error is measured in an $L_q$-norm with matching upper and lower bounds. The end result is a reconciliation between minimax rates and optimal recovery rates. The NLA minimax rate continuously depends on the noise level and recovers the optimal recovery rate when $σ$ tends to zero.
title Optimal Recovery Meets Minimax Estimation
topic Statistics Theory
Numerical Analysis
Machine Learning
url https://arxiv.org/abs/2502.17671