Nonparametric Exponential Family Regression Under Star-Shaped Constraints

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Guanghong, Neykov, Matey
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916652343361536
author Yi, Guanghong
Neykov, Matey
author_facet Yi, Guanghong
Neykov, Matey
contents We study the minimax rate of estimation in nonparametric exponential family regression under star-shaped constraints. Specifically, the parameter space $K$ is a star-shaped set contained within a bounded box $[-M, M]^n$, where $M$ is a known positive constant. Moreover, we assume that the exponential family is nonsingular and that its cumulant function is twice continuously differentiable. Our main result shows that the minimax rate for this problem is $\varepsilon^{*2} \wedge \operatorname{diam}(K)^2$, up to absolute constants, where $\varepsilon^*$ is defined as \[ \varepsilon^* = \sup \{\varepsilon: \varepsilon^2 κ(M) \leq \log N^{\operatorname{loc}}(\varepsilon)\}, \] with $N^{\operatorname{loc}}(\varepsilon)$ denoting the local entropy and $κ(M)$ is an absolute constant allowed to depend on $M$. We also provide an example and derive its corresponding minimax optimal rate.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nonparametric Exponential Family Regression Under Star-Shaped Constraints
Yi, Guanghong
Neykov, Matey
Statistics Theory
We study the minimax rate of estimation in nonparametric exponential family regression under star-shaped constraints. Specifically, the parameter space $K$ is a star-shaped set contained within a bounded box $[-M, M]^n$, where $M$ is a known positive constant. Moreover, we assume that the exponential family is nonsingular and that its cumulant function is twice continuously differentiable. Our main result shows that the minimax rate for this problem is $\varepsilon^{*2} \wedge \operatorname{diam}(K)^2$, up to absolute constants, where $\varepsilon^*$ is defined as \[ \varepsilon^* = \sup \{\varepsilon: \varepsilon^2 κ(M) \leq \log N^{\operatorname{loc}}(\varepsilon)\}, \] with $N^{\operatorname{loc}}(\varepsilon)$ denoting the local entropy and $κ(M)$ is an absolute constant allowed to depend on $M$. We also provide an example and derive its corresponding minimax optimal rate.
title Nonparametric Exponential Family Regression Under Star-Shaped Constraints
topic Statistics Theory
url https://arxiv.org/abs/2503.10794