Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Differentiable Multiple Shooting Layers
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace the Latent Neural ODE decoder with a vMSL decoder | latent sequence generation model · Noisy-observation sequence generation | NFEs per training iteration and sample generation: 60% less NFEs | Helped |
| replace the Latent Neural ODE decoder with a vMSL decoder | latent sequence generation model · Noisy-observation sequence generation | sample quality | No clear effect |
| use MSL fixed-point tracking instead of sequential Neural ODE inference | controlled limit-cycle trajectories · Limit cycle stabilization | NFEs for trajectory inference: 8 NFE; >3000 NFE | Helped |
| use MSL with forward sensitivity instead of sequential RK4 integration | Timoshenko beam boundary controller · Timoshenko beam boundary control | wall-clock time per training iteration: three time faster | Helped |
| use zeroth-order MSL inference instead of the baseline RK4 Neural CDE | Neural CDE for sepsis prediction · PhysioNet 2019 sepsis prediction | total wall-clock time to convergence: one order of magnitude smaller | Helped |
Closest papers by meaning
- Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations (NeurIPS 2026 · similarity 0.88)
- How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective (ICML 2024 · similarity 0.85)
- Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations (ICML 2024 · similarity 0.84)
- Semi-Implicit Neural Ordinary Differential Equations (AAAI 2025 · similarity 0.83)
- Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions (NeurIPS 2025 · similarity 0.83)
- Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models (NeurIPS 2025 · similarity 0.83)
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.