Onsager-Machlup functional for stochastic differential equations with time-varying noise

TL;DR

This paper derives the Onsager-Machlup functional for stochastic differential equations with time-varying noise, extending the theory to more realistic models where diffusion coefficients change over time, and demonstrates applications through numerical simulations.

Contribution

It introduces a novel Onsager-Machlup functional for SDEs with time-dependent diffusion, using new norms and Girsanov transformation, expanding the theoretical framework for such stochastic processes.

Findings

Derived the Onsager-Machlup functional for time-varying noise SDEs.

Numerical simulations demonstrate the functional's application to multiscale models.

Showed the significant impact of time-varying diffusion on transition paths.

Abstract

This paper is devoted to studying the Onsager-Machlup functional for stochastic differential equations with time-varying noise of the {\alpha}-H\"older, 0<{\alpha}<1/4, dXt =f(t,Xt)dt+g(t)dWt. Our study focuses on scenarios where the diffusion coefficient g(t) exhibits temporal variability, starkly contrasting the conventional assumption of a constant diffusion coefficient in the existing literature. This variance brings some complexity to the analysis. Through this investigation, we derive the Onsager-Machlup functional, which acts as the Lagrangian for mapping the most probable transition path between metastable states in stochastic processes affected by time-varying noise. This is done by introducing new measurable norms and applying an appropriate version of the Girsanov transformation. To illustrate our theoretical advancements, we provide numerical simulations, including cases of a one-dimensional SDE and a fast-slow SDE system, which demonstrate the application to multiscale stochastic volatility models, thereby highlighting the significant impact of time-varying diffusion coefficients.