Improving the Noise Estimation of Latent Neural Stochastic Differential Equations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912421355978752 |
|---|---|
| author | Heck, Linus Gelbrecht, Maximilian Schaub, Michael T. Boers, Niklas |
| author_facet | Heck, Linus Gelbrecht, Maximilian Schaub, Michael T. Boers, Niklas |
| contents | Latent neural stochastic differential equations (SDEs) have recently emerged as a promising approach for learning generative models from stochastic time series data. However, they systematically underestimate the noise level inherent in such data, limiting their ability to capture stochastic dynamics accurately. We investigate this underestimation in detail and propose a straightforward solution: by including an explicit additional noise regularization in the loss function, we are able to learn a model that accurately captures the diffusion component of the data. We demonstrate our results on a conceptual model system that highlights the improved latent neural SDE's capability to model stochastic bistable dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_17499 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving the Noise Estimation of Latent Neural Stochastic Differential Equations Heck, Linus Gelbrecht, Maximilian Schaub, Michael T. Boers, Niklas Machine Learning Latent neural stochastic differential equations (SDEs) have recently emerged as a promising approach for learning generative models from stochastic time series data. However, they systematically underestimate the noise level inherent in such data, limiting their ability to capture stochastic dynamics accurately. We investigate this underestimation in detail and propose a straightforward solution: by including an explicit additional noise regularization in the loss function, we are able to learn a model that accurately captures the diffusion component of the data. We demonstrate our results on a conceptual model system that highlights the improved latent neural SDE's capability to model stochastic bistable dynamics. |
| title | Improving the Noise Estimation of Latent Neural Stochastic Differential Equations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2412.17499 |