New Bootstrap Method Proposed for Inference in Riemannian Stochastic Approximation
Researchers introduce an online multiplier bootstrap for manifold-valued parameters estimated by averaging the iterates of Riemannian stochastic approximation, enabling statistical inference for such optimization methods.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-03 05:00 · arXiv stat.ML
Bootstrap Inference for Riemannian Optimization Problems