Efficient Training of Neural SDEs Using Stochastic Optimal Control
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909620862189568 |
|---|---|
| author | Daems, Rembert Opper, Manfred Crevecoeur, Guillaume Birdal, Tolga |
| author_facet | Daems, Rembert Opper, Manfred Crevecoeur, Guillaume Birdal, Tolga |
| contents | We present a hierarchical, control theory inspired method for variational inference (VI) for neural stochastic differential equations (SDEs). While VI for neural SDEs is a promising avenue for uncertainty-aware reasoning in time-series, it is computationally challenging due to the iterative nature of maximizing the ELBO. In this work, we propose to decompose the control term into linear and residual non-linear components and derive an optimal control term for linear SDEs, using stochastic optimal control. Modeling the non-linear component by a neural network, we show how to efficiently train neural SDEs without sacrificing their expressive power. Since the linear part of the control term is optimal and does not need to be learned, the training is initialized at a lower cost and we observe faster convergence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17150 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Training of Neural SDEs Using Stochastic Optimal Control Daems, Rembert Opper, Manfred Crevecoeur, Guillaume Birdal, Tolga Machine Learning Artificial Intelligence Probability We present a hierarchical, control theory inspired method for variational inference (VI) for neural stochastic differential equations (SDEs). While VI for neural SDEs is a promising avenue for uncertainty-aware reasoning in time-series, it is computationally challenging due to the iterative nature of maximizing the ELBO. In this work, we propose to decompose the control term into linear and residual non-linear components and derive an optimal control term for linear SDEs, using stochastic optimal control. Modeling the non-linear component by a neural network, we show how to efficiently train neural SDEs without sacrificing their expressive power. Since the linear part of the control term is optimal and does not need to be learned, the training is initialized at a lower cost and we observe faster convergence. |
| title | Efficient Training of Neural SDEs Using Stochastic Optimal Control |
| topic | Machine Learning Artificial Intelligence Probability |
| url | https://arxiv.org/abs/2505.17150 |