Trajectory Flow Matching with Applications to Clinical Time Series Modeling
This addresses scalability and stability issues in Neural SDE training for clinical time series modeling, representing an incremental improvement over existing methods.
The paper tackles the challenge of training neural stochastic differential equations (Neural SDEs) for modeling stochastic and irregularly sampled time series, especially in medicine, by proposing Trajectory Flow Matching (TFM), a simulation-free method that bypasses backpropagation through SDE dynamics, resulting in improved performance and uncertainty prediction on three clinical datasets.
Modeling stochastic and irregularly sampled time series is a challenging problem found in a wide range of applications, especially in medicine. Neural stochastic differential equations (Neural SDEs) are an attractive modeling technique for this problem, which parameterize the drift and diffusion terms of an SDE with neural networks. However, current algorithms for training Neural SDEs require backpropagation through the SDE dynamics, greatly limiting their scalability and stability. To address this, we propose Trajectory Flow Matching (TFM), which trains a Neural SDE in a simulation-free manner, bypassing backpropagation through the dynamics. TFM leverages the flow matching technique from generative modeling to model time series. In this work we first establish necessary conditions for TFM to learn time series data. Next, we present a reparameterization trick which improves training stability. Finally, we adapt TFM to the clinical time series setting, demonstrating improved performance on three clinical time series datasets both in terms of absolute performance and uncertainty prediction.