Training-free score-based diffusion for parameter-dependent stochastic dynamical systems

TL;DR

This paper introduces a training-free, conditional diffusion model for efficiently simulating parameter-dependent stochastic differential equations, enabling rapid generation of trajectories across continuous parameter ranges without retraining.

Contribution

The paper proposes a novel joint kernel-weighted Monte Carlo estimator for conditional score functions, allowing interpolation over parameters without neural network training.

Findings

Accurately approximates conditional distributions across parameters

Enables real-time trajectory generation without retraining

Demonstrates effectiveness on complex numerical examples

Abstract

Simulating parameter-dependent stochastic differential equations (SDEs) presents significant computational challenges, as separate high-fidelity simulations are typically required for each parameter value of interest. Despite the success of machine learning methods in learning SDE dynamics, existing approaches either require expensive neural network training for score function estimation or lack the ability to handle continuous parameter dependence. We present a training-free conditional diffusion model framework for learning stochastic flow maps of parameter-dependent SDEs, where both drift and diffusion coefficients depend on physical parameters. The key technical innovation is a joint kernel-weighted Monte Carlo estimator that approximates the conditional score function using trajectory data sampled at discrete parameter values, enabling interpolation across both state space and the continuous parameter domain. Once trained, the resulting generative model produces sample trajectories for any parameter value within the training range without retraining, significantly accelerating parameter studies, uncertainty quantification, and real-time filtering applications. The performance of the proposed approach is demonstrated via three numerical examples of increasing complexity, showing accurate approximation of conditional distributions across varying parameter values.