Bootstrap Inference for Riemannian Optimization Problems
Abstract
We develop an online multiplier bootstrap for manifold-valued parameters estimated by averaging the iterates of Riemannian stochastic approximation. The method runs weighted iterations alongside the original algorithm, with each path using the same observations while updating its own state and intrinsic average. The weighted averages provide uncertainty assessments without a plug-in asymptotic covariance estimator. Under local stability and regularity conditions, we establish bootstrap consistency and show that a fixed number of paths suffices for asymptotically valid Student intervals and intrinsic confidence regions. The theory accommodates samplewise nonsmooth scores and identifies a critical oracle-bias regime in which the estimator's limiting distribution shifts, but the centered bootstrap distribution does not. Applications include spherical means, positive-definite matrix means and medians, and principal-subspace estimation. Simulations show coverage close to nominal in regular settings, and an analysis of North Atlantic storm locations illustrates descriptive online inference for a spherical center.
Related
- Shape Optimization and Bernoulli Free Boundary Problems for the Riemannian p-Laplacian
- Riemannian optimization for linear optical problems
- Locally Private Inference for Riemannian Stochastic Optimization
- Generalized Bayesian Inference using the Bayesian Bootstrap for Survival Models
- Post-Inference Model Chaining: A Problem Statement and a Model-based Bootstrap for Training End-to-End Digital Twins
BibTeX
@misc{chang2026bootstrap,
title = {{Bootstrap Inference for Riemannian Optimization Problems}},
author = {Xiaotian Chang and Qirui Hu and Yangdi Jiang and Nan Qiao},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.00947},
eprint = {2611.00947},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.00947},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Bootstrap Inference for Riemannian Optimization Problems
AU - Xiaotian Chang
AU - Qirui Hu
AU - Yangdi Jiang
AU - Nan Qiao
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.00947
UR - https://arxiv.org/abs/2611.00947
AB - We develop an online multiplier bootstrap for manifold-valued parameters estimated by averaging the iterates of Riemannian stochastic approximation. The method runs weighted iterations alongside the original algorithm, with each path using the same observations while updating its own state and intrinsic average. The weighted averages provide uncertainty assessments without a plug-in asymptotic covariance estimator. Under local stability and regularity conditions, we establish bootstrap consistency and show that a fixed number of paths suffices for asymptotically valid Student intervals and intrinsic confidence regions. The theory accommodates samplewise nonsmooth scores and identifies a critical oracle-bias regime in which the estimator's limiting distribution shifts, but the centered bootstrap distribution does not. Applications include spherical means, positive-definite matrix means and medians, and principal-subspace estimation. Simulations show coverage close to nominal in regular settings, and an analysis of North Atlantic storm locations illustrates descriptive online inference for a spherical center.
ER -