Fast rates for the classification of Ornstein-Uhlenbeck paths
Abstract
In binary classification problems, plug-in classifiers can sometimes achieve faster excess risk rates than the underlying estimation rate. In this work, we study a supervised classification problem based on repeated independent observations of Ornstein-Uhlenbeck paths, with both time-homogeneous and time-inhomogeneous drifts. We show that, under a suitable separation condition on the class-dependent drifts, a plug-in classifier attains an excess risk of quadratic order in the corresponding parametric or nonparametric estimation error. The theoretical approach utilizes the Wiener chaos representation and spectral theory to characterize the log-likelihood ratio as a quadratic form of Gaussian random variables, enabling a precise analysis of margin behaviour and deviation results. This extends the fast-rate results from classification problems with linear discriminant models and Gaussian white noise models to dynamical diffusion systems with Gaussian structure.
Related
- Fourier-Laplace transforms in polynomial Ornstein-Uhlenbeck volatility models
- Sharp Logarithmic Sobolev Inequalities for q-Araki-Woods Ornstein-Uhlenbeck Semigroups
- Ornstein-Uhlenbeck Is Hard to Beat, Yet Superlinear Drift Ships Lower Transport Costs
- PSEUDOSPECTRAL PHENOMENA PREVENTING THE ANALYTICITY SECTOR OF A ORNSTEIN-UHLENBECK SEMIGROUP TO BE RULED BY THE SPECTRAL ANGLE OF ITS GENERATOR
- Spectral and mapping properties of the inverse Ornstein--Uhlenbeck operator
BibTeX
@misc{meng2026fast,
title = {{Fast rates for the classification of Ornstein-Uhlenbeck paths}},
author = {Shanshan Meng and Markus Reiß},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.39726},
eprint = {2610.39726},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.39726},
}
RIS
TY - UNPB
TI - Fast rates for the classification of Ornstein-Uhlenbeck paths
AU - Shanshan Meng
AU - Markus Reiß
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.39726
UR - https://arxiv.org/abs/2610.39726
AB - In binary classification problems, plug-in classifiers can sometimes achieve faster excess risk rates than the underlying estimation rate. In this work, we study a supervised classification problem based on repeated independent observations of Ornstein-Uhlenbeck paths, with both time-homogeneous and time-inhomogeneous drifts. We show that, under a suitable separation condition on the class-dependent drifts, a plug-in classifier attains an excess risk of quadratic order in the corresponding parametric or nonparametric estimation error. The theoretical approach utilizes the Wiener chaos representation and spectral theory to characterize the log-likelihood ratio as a quadratic form of Gaussian random variables, enabling a precise analysis of margin behaviour and deviation results. This extends the fast-rate results from classification problems with linear discriminant models and Gaussian white noise models to dynamical diffusion systems with Gaussian structure.
ER -