提出无需仿真即可训练潜在随机微分方程的新方法，显著降低计算开销。
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
- 基于得分与流匹配思想，设计无仿真训练框架
- 性能媲美传统方法，计算复杂度大幅下降
- 适合大规模时间序列建模，尤其关注效率的场景
潜在随机微分方程（Latent SDE）是时间序列与序列建模的强大工具。然而，现有训练方法通常依赖伴随敏感性方法，需通过近似SDE解进行模拟与反向传播，限制了可扩展性。本文提出SDE Matching，一种全新的无仿真训练方法。受现代得分与流匹配算法启发，将这些思想拓展至时间序列建模中的随机动力学领域，彻底避免了昂贵的数值模拟。实验表明，SDE Matching在性能上可媲美伴随敏感性方法，同时显著降低计算复杂度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。