Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Accelerating Neural ODEs: A Variational Formulation-based Approach
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes VF-NODE, a variational-formulation-based training approach for Neural ODEs that avoids repeated numerical ODE solving to speed up training and reduce accumulated autoregressive error.
Problem
Training Neural ODEs on irregularly sampled observational data relies on numerical ODE solvers, which are slow and accumulate numerical errors over time due to autoregression.
Approach
Replaces numerical ODE solver-based training with a variational formulation of the Neural ODE objective, so the model is trained without repeatedly integrating the dynamics (based on the abstract; details not available).
Experimental setup
Builds on: Neural ODE
Closest papers by meaning
- From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems (ICML 2024 · similarity 0.90)
- Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach (AAAI 2024 · similarity 0.90)
- ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence (NeurIPS 2024 · similarity 0.89)
- How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective (ICML 2024 · similarity 0.89)
- Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations (ICLR 2025 · similarity 0.89)
- Simulation-Free Training of Neural ODEs on Paired Data (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.