Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions
Naoki Kiyohara, Edward Johns, Yingzhen Li
Abstract
Stochastic differential equations (SDEs) are well suited to modelling noisy and/or irregularly-sampled time series, which are omnipresent in finance, physics, and machine learning applications. Traditional approaches require costly simulation of numerical solvers when sampling between arbitrary time points. We introduce Neural Stochastic Flows (NSFs) and their latent dynamic versions, which learns (latent) SDE transition laws directly using conditional normalising flows, with architectural constraints that preserve properties inherited from stochastic flow. This enables sampling between arbitrary states in a single step, providing up to two orders of magnitude speedup for distant time points. Experiments on synthetic SDE simulations and real-world tracking and video data demonstrate that NSF maintains distributional accuracy comparable to numerical approaches while dramatically reducing computation for arbitrary time-point sampling, enabling applications where numerical solvers remain prohibitively expensive.
BibTeX
@inproceedings{
kiyohara2025neural,
title={Neural Stochastic Flows: Solver-Free Modelling and Inference for {SDE} Solutions},
author={Naoki Kiyohara and Edward Johns and Yingzhen Li},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=PrYDDxphym}
}