Salvato in:
Dettagli Bibliografici
Autori principali: Kang, Benjamin, Polyanskiy, Yury, Teh, Anzo
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.18689
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917223915847680
author Kang, Benjamin
Polyanskiy, Yury
Teh, Anzo
author_facet Kang, Benjamin
Polyanskiy, Yury
Teh, Anzo
contents We study function estimation in the empirical Bayes setting for Poisson and normal means. Specifically, given observations $Y_i\sim f(\cdot; θ_i)$ with latent parameters $θ_i\sim π$, the goal is to estimate $\mathbb{E}_π[\ell(θ)|X = x]$. This task lies between classical deconvolution (recovering the full prior $π$), and standard empirical Bayes mean estimation. While the minimax risk for estimating $π$ in the Wasserstein distance is known to decay only logarithmically, we show that estimating certain smooth functions admits dramatically faster rates. In particular, for polynomial functions of degree $k$ in the Poisson model, we establish a tight bound of $Θ(\frac{1}{n}(\frac{\log n}{\log \log n})^{k+1})$ and $Θ(\frac{1}{n}(\log n)^{2k+1})$ for bounded and subexponential priors, respectively, attainable by estimators mimicking those that achieve optimal regret for the mean estimation problem (Robbins, mininum distance, ERM). Our analysis identifies the approximation-theoretic origin of this improvement: smooth functions can be well-approximated by low-degree polynomials, whereas Lipschitz functions require dense polynomial approximations, incurring a $\frac{1}{k}$ loss for degree $k$ polynomial approximation. The results reveal a sharp hierarchy in the difficulty of empirical Bayes problems: ranging from slow, logarithmic deconvolution to near-parametric convergence for smooth posterior functionals, and establish new connections between nonparametric empirical Bayes theory, polynomial approximation, and statistical inverse problems. Finally, we complement our analysis with a lower bound of $Ω(\frac 1n (\frac{\log n}{\log \log n})^{k+1})$ (bounded priors) and $Ω(\frac 1n (\log n)^{k + 1})$ (subgaussian priors) for the normal means model.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18689
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Function estimation in the empirical Bayes setting
Kang, Benjamin
Polyanskiy, Yury
Teh, Anzo
Statistics Theory
We study function estimation in the empirical Bayes setting for Poisson and normal means. Specifically, given observations $Y_i\sim f(\cdot; θ_i)$ with latent parameters $θ_i\sim π$, the goal is to estimate $\mathbb{E}_π[\ell(θ)|X = x]$. This task lies between classical deconvolution (recovering the full prior $π$), and standard empirical Bayes mean estimation. While the minimax risk for estimating $π$ in the Wasserstein distance is known to decay only logarithmically, we show that estimating certain smooth functions admits dramatically faster rates. In particular, for polynomial functions of degree $k$ in the Poisson model, we establish a tight bound of $Θ(\frac{1}{n}(\frac{\log n}{\log \log n})^{k+1})$ and $Θ(\frac{1}{n}(\log n)^{2k+1})$ for bounded and subexponential priors, respectively, attainable by estimators mimicking those that achieve optimal regret for the mean estimation problem (Robbins, mininum distance, ERM). Our analysis identifies the approximation-theoretic origin of this improvement: smooth functions can be well-approximated by low-degree polynomials, whereas Lipschitz functions require dense polynomial approximations, incurring a $\frac{1}{k}$ loss for degree $k$ polynomial approximation. The results reveal a sharp hierarchy in the difficulty of empirical Bayes problems: ranging from slow, logarithmic deconvolution to near-parametric convergence for smooth posterior functionals, and establish new connections between nonparametric empirical Bayes theory, polynomial approximation, and statistical inverse problems. Finally, we complement our analysis with a lower bound of $Ω(\frac 1n (\frac{\log n}{\log \log n})^{k+1})$ (bounded priors) and $Ω(\frac 1n (\log n)^{k + 1})$ (subgaussian priors) for the normal means model.
title Function estimation in the empirical Bayes setting
topic Statistics Theory
url https://arxiv.org/abs/2601.18689