Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Second-Order Complexity of Neural ODE Inference
Yoshihiro Maruyama
Read the paperCheck your idea against 137,217 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.
Studies the computational complexity of neural ODE inference as the flow endpoint of a learned vector field computed to requested accuracy, using second-order complexity analysis under compactness and Lipschitz assumptions.
Problem
The cost of the global forward pass of neural ODEs, where inference is the flow endpoint of a learned vector field computed to a requested accuracy, under standard compactness and Lipschitz certificates.
Approach
Frames neural ODE inference as a second-order complexity problem, analyzing the flow endpoint map as a computable operator under standard compactness and Lipschitz certificates rather than as a fixed finite layer stack.
Closest papers by meaning
- Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks (ICML 2022 · similarity 0.89)
- On Second Order Behaviour in Augmented Neural ODEs (NeurIPS 2020 · similarity 0.88)
- How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective (ICML 2024 · similarity 0.88)
- Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure (AAAI 2025 · similarity 0.87)
- Breakeven complexity: A new perspective on neural partial differential equation solvers (NeurIPS 2026 · similarity 0.87)
- Global Convergence in Neural ODEs: Impact of Activation Functions (ICLR 2025 · similarity 0.86)
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.
