Poster
in
Workshop: Structured Probabilistic Inference and Generative Modeling
Conditional Flow Matching for Time Series Modelling
Ella Tamir · Najwa Laabid · Markus Heinonen · Vikas Garg · Arno Solin
Keywords: [ Conditional Flow Matching ] [ Neural ODEs ] [ Time-Series Modelling ]
Learning dynamical systems from long trajectories is a challenging problem due to the complexity of the loss landscape. Inspired by conditional flow matching in generative modeling, we propose a new approach for training neural ODEs based on regressing vector fields of conditional probability paths defined per trajectory. Our Conditional Flow Matching for Time Series (CFM-TS) objective outperforms neural ODEs trained with the adjoint method on three simulated tasks, including a pendulum system where the neural ODE loss does not converge at all.