On a Universal Strictly Decreasing Nonparametric Estimator Applied to the Drift Function of a Recurrent Diffusion Process Estimation
arXiv:2603.14037
The paper proposes a continuously differentiable, strictly decreasing nonparametric estimator for the drift function of recurrent diffusion processes, providing non‑asymptotic L¹ risk bounds and a data‑driven bandwidth selection method.
Abstract
This paper deals with a copies-based continuously differentiable and strictly decreasing estimator of the drift function for stochastic differential equations defining recurrent diffusion processes. The first part of our paper deals with non-asymptotic -risk bounds and a bandwidths selection procedure for a universal monotone estimator. These results are tailor-made to our framework, and then applied to the estimation of the drift function of recurrent diffusion processes in the second part of the paper.
17 pages, 2 figures