Sharp Bounds for Near-Maximizers of Gaussian Processes

For a centered Gaussian process $G$ with continuous sample paths on a compact metric space $T$, a continuous drift $f: T \mapsto \mathbb{R}$, a noise level $σ>0$, and $ε\ge 0$, let $A_ε$ be the set of points at which $f+σG$ is within $ε$ of its maximum. Writing $\mathbb{E}\sup_TG$ for the expected supremum of $G$, we prove that the expected squared diameter of $A_ε$ in the canonical pseudometric of $G$ is at most $8ε\mathbb{E}\sup_TG/σ$ and that the expected maximal squared distance from a point of $A_ε$ to an exact maximizer is at most $4ε\mathbb{E}\sup_TG/σ$. The constants cannot be improved uniformly over index sets, processes, and drifts, and no logarithmic factor in $ε$ appears, unlike in bounds integrated from tail estimates. At $ε=0$ the bounds give the almost sure uniqueness of the maximizer in the canonical pseudometric without nondegeneracy assumptions. Given this uniqueness, both bounds follow from a bound with constant $2$ on the mean square of the largest increment of an independent copy of $G$ from an exact maximizer to a point of $A_ε$. The proof rests on an identity for the mean squared support function of the $ε$-subdifferentials of a smooth convex function at a standard Gaussian vector, obtained from two Gaussian integrations by parts.

Authors

Institutions

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.16233
Primary Topic
Probability and Statistical Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Sharp Bounds for Near-Maximizers of Gaussian Processes

Hirofumi Ota
arXiv (Cornell University)
Probability and Statistical Research
preprint

Sharp Bounds for Near-Maximizers of Gaussian Processes

Hirofumi Ota
preprint en

Abstract

For a centered Gaussian process $G$ with continuous sample paths on a compact metric space $T$, a continuous drift $f: T \mapsto \mathbb{R}$, a noise level $σ>0$, and $ε\ge 0$, let $A_ε$ be the set of points at which $f+σG$ is within $ε$ of its maximum. Writing $\mathbb{E}\sup_TG$ for the expected supremum of $G$, we prove that the expected squared diameter of $A_ε$ in the canonical pseudometric of $G$ is at most $8ε\mathbb{E}\sup_TG/σ$ and that the expected maximal squared distance from a point of $A_ε$ to an exact maximizer is at most $4ε\mathbb{E}\sup_TG/σ$. The constants cannot be improved uniformly over index sets, processes, and drifts, and no logarithmic factor in $ε$ appears, unlike in bounds integrated from tail estimates. At $ε=0$ the bounds give the almost sure uniqueness of the maximizer in the canonical pseudometric without nondegeneracy assumptions. Given this uniqueness, both bounds follow from a bound with constant $2$ on the mean square of the largest increment of an independent copy of $G$ from an exact maximizer to a point of $A_ε$. The proof rests on an identity for the mean squared support function of the $ε$-subdifferentials of a smooth convex function at a standard Gaussian vector, obtained from two Gaussian integrations by parts.

arXiv (Cornell University)
The University of Tokyo (JP)
Probability and Statistical Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon