SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918070961831936 |
|---|---|
| author | Bartosh, Grigory Vetrov, Dmitry Naesseth, Christian A. |
| author_facet | Bartosh, Grigory Vetrov, Dmitry Naesseth, Christian A. |
| contents | The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend on simulation and backpropagation through approximate SDE solutions, which limit scalability. In this work, we propose SDE Matching, a new simulation-free method for training Latent SDEs. Inspired by modern Score- and Flow Matching algorithms for learning generative dynamics, we extend these ideas to the domain of stochastic dynamics for time series and sequence modeling, eliminating the need for costly numerical simulations. Our results demonstrate that SDE Matching achieves performance comparable to adjoint sensitivity methods while drastically reducing computational complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02472 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations Bartosh, Grigory Vetrov, Dmitry Naesseth, Christian A. Machine Learning The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend on simulation and backpropagation through approximate SDE solutions, which limit scalability. In this work, we propose SDE Matching, a new simulation-free method for training Latent SDEs. Inspired by modern Score- and Flow Matching algorithms for learning generative dynamics, we extend these ideas to the domain of stochastic dynamics for time series and sequence modeling, eliminating the need for costly numerical simulations. Our results demonstrate that SDE Matching achieves performance comparable to adjoint sensitivity methods while drastically reducing computational complexity. |
| title | SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.02472 |