Sharp functional quantization and empirical Wasserstein rates for Itô processes
Abstract
We establish functional quantization and empirical Wasserstein rates for continuous Itô processes under the supremum norm. We assume that the initial condition and the drift and diffusion integrands are controlled by a time-uniform random upper bound with a finite ρ-moment for some ρ>1. Under this assumption, the n-point Lq quantization error is at most C(log n)−1/2 for every 1≤ q<ρ. The known Brownian lower bound shows that the exponent 1/2 is optimal over this class. Our proof combines an adaptive dyadic time partition with localization according to the size of the integrands. A general transfer principle yields the sharp mean rate (log N)−1/2 for the p-Wasserstein distance between the empirical law of N independent copies and their common path law, together with nonasymptotic deviation bounds, whenever 1≤ p<ρ. Applications include empirical path-law estimates for path-dependent SDEs and a path-space limit-theory estimate for path-dependent McKean--Vlasov interacting particle systems with common noise.
Related
- Dimension-free Convergence Rate in Sliced Wasserstein Distance for Empirical Measures of Markov Processes
- On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study
- Sharp inequalities between Zolotarev and Wasserstein distances in 𝒫2(ℝd)
- Graph-diameter criteria and sharp dissipation in discrete Wasserstein-Fisher geometry
- Sharp Wasserstein stability and small-delay thresholds for evolution equations with measure-valued principal-part delays
BibTeX
@misc{he2026sharp,
title = {{Sharp functional quantization and empirical Wasserstein rates for Itô processes}},
author = {Xihao He and Fengyi Yuan},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.07879},
eprint = {2608.07879},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.07879},
}
RIS
TY - UNPB
TI - Sharp functional quantization and empirical Wasserstein rates for Itô processes
AU - Xihao He
AU - Fengyi Yuan
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2608.07879
UR - https://arxiv.org/abs/2608.07879
AB - We establish functional quantization and empirical Wasserstein rates for continuous Itô processes under the supremum norm. We assume that the initial condition and the drift and diffusion integrands are controlled by a time-uniform random upper bound with a finite ρ-moment for some ρ>1. Under this assumption, the n-point L^q quantization error is at most C(log n)^−1/2 for every 1≤ q<ρ. The known Brownian lower bound shows that the exponent 1/2 is optimal over this class. Our proof combines an adaptive dyadic time partition with localization according to the size of the integrands. A general transfer principle yields the sharp mean rate (log N)^−1/2 for the p-Wasserstein distance between the empirical law of N independent copies and their common path law, together with nonasymptotic deviation bounds, whenever 1≤ p<ρ. Applications include empirical path-law estimates for path-dependent SDEs and a path-space limit-theory estimate for path-dependent McKean--Vlasov interacting particle systems with common noise.
ER -