Sharp bounds for stochastic proximal and projection estimators via radial dominance
Abstract
We study stochastic barycentric estimators for proximal points and metric projections obtained by exponentially reweighting Gaussian perturbations. Our main result is an abstract comparison theorem for probability measures with densities proportional to an exponential weight, under a radial dominance condition relative to a prescribed profile. This yields an explicit upper bound for the norm of the associated barycenter in terms of a one-dimensional comparison measure. We also provide tractable sufficient conditions for radial dominance, including strong convexity, addition of nonnegative convex terms, and star-shaped constraints. As a consequence, we obtain a refined convergence rate for stochastic proximal estimators of weakly convex functions, together with asymptotic sharpness of the constant. The same framework yields a corresponding rate for stochastic projection estimators onto closed convex sets. We further establish basic structural properties of the barycentric approximation operator, such as smoothness and cocoercivity. Numerical experiments illustrate the predicted rate, the dimensional scaling of the constant, and its asymptotic sharpness.
Related
- Stochastic dominance of first return times for nearest-neighbor random walks on ℤd
- Error Bounds for Statistical Estimators in BTL Model with Parametric Multivariate Utility Functions
- Testing Conditional Stochastic Dominance via Copula Derivatives
- Tractable Relaxations of Multivariate Stochastic Dominance via Optimal Transport and CVaR
- Invariant Measures as Estimators: Second-Order Stochastic Expansions and Bias Reduction
BibTeX
@misc{contador2026sharp,
title = {{Sharp bounds for stochastic proximal and projection estimators via radial dominance}},
author = {Gonzalo Contador and Pedro Pérez-Aros and Emilio Vilches},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.08670},
eprint = {2607.08670},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.08670},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Sharp bounds for stochastic proximal and projection estimators via radial dominance
AU - Gonzalo Contador
AU - Pedro Pérez-Aros
AU - Emilio Vilches
PY - 2026
DA - 2026/09/13
PB - arXiv
DO - 10.48550/arxiv.2607.08670
UR - https://arxiv.org/abs/2607.08670
AB - We study stochastic barycentric estimators for proximal points and metric projections obtained by exponentially reweighting Gaussian perturbations. Our main result is an abstract comparison theorem for probability measures with densities proportional to an exponential weight, under a radial dominance condition relative to a prescribed profile. This yields an explicit upper bound for the norm of the associated barycenter in terms of a one-dimensional comparison measure. We also provide tractable sufficient conditions for radial dominance, including strong convexity, addition of nonnegative convex terms, and star-shaped constraints. As a consequence, we obtain a refined convergence rate for stochastic proximal estimators of weakly convex functions, together with asymptotic sharpness of the constant. The same framework yields a corresponding rate for stochastic projection estimators onto closed convex sets. We further establish basic structural properties of the barycentric approximation operator, such as smoothness and cocoercivity. Numerical experiments illustrate the predicted rate, the dimensional scaling of the constant, and its asymptotic sharpness.
ER -