Saved in:
Bibliographic Details
Main Authors: Kroshnin, Alexey, Spokoiny, Vladimir, Suvorikova, Alexandra
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2111.12612
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916493252362240
author Kroshnin, Alexey
Spokoiny, Vladimir
Suvorikova, Alexandra
author_facet Kroshnin, Alexey
Spokoiny, Vladimir
Suvorikova, Alexandra
contents This study focuses on finite-sample inference on the non-linear Bures-Wasserstein manifold and introduces a generalized bootstrap procedure for estimating Bures-Wasserstein barycenters. We provide non-asymptotic statistical guarantees for the resulting bootstrap confidence sets. The proposed approach incorporates classical resampling methods, including the multiplier bootstrap highlighted as a specific example. Additionally, the paper compares bootstrap-based confidence sets with asymptotic sets obtained in the work arXiv:1901.00226v2, evaluating their statistical performance and computational complexities. The methodology is validated through experiments on synthetic datasets and real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2111_12612
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Generalized bootstrap in the Bures-Wasserstein space
Kroshnin, Alexey
Spokoiny, Vladimir
Suvorikova, Alexandra
Statistics Theory
Applications
62F40
This study focuses on finite-sample inference on the non-linear Bures-Wasserstein manifold and introduces a generalized bootstrap procedure for estimating Bures-Wasserstein barycenters. We provide non-asymptotic statistical guarantees for the resulting bootstrap confidence sets. The proposed approach incorporates classical resampling methods, including the multiplier bootstrap highlighted as a specific example. Additionally, the paper compares bootstrap-based confidence sets with asymptotic sets obtained in the work arXiv:1901.00226v2, evaluating their statistical performance and computational complexities. The methodology is validated through experiments on synthetic datasets and real-world applications.
title Generalized bootstrap in the Bures-Wasserstein space
topic Statistics Theory
Applications
62F40
url https://arxiv.org/abs/2111.12612