Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Generalization bounds for neural ordinary differential equations and deep residual networks
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 |
|---|---|---|---|
| add penalization on the sum of squared Frobenius norms of successive weight differences | deep residual network (width 30, depth 1000) · MNIST | generalization gap (cross-entropy) | Helped |
| penalize the maximum max-norm of weight differences instead of the Frobenius-based term (ablation) | deep residual network · MNIST | generalization gap (cross-entropy) | No clear effect |
| penalize the L2 norm of the max-norm of weight differences (ablation) | deep residual network · MNIST | generalization gap (cross-entropy) | Helped |
Closest papers by meaning
- Implicit regularization of deep residual networks towards neural ODEs (ICLR 2024 · similarity 0.91)
- Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss (ICML 2024 · similarity 0.87)
- Generalization of Scaled Deep ResNets in the Mean-Field Regime (ICLR 2024 · similarity 0.87)
- Generalization Bounds for Rank-sparse Neural Networks (NeurIPS 2025 · similarity 0.87)
- Fantastic Generalization Measures are Nowhere to be Found (ICLR 2024 · similarity 0.87)
- On the Generalization and Approximation Capacities of Neural Controlled Differential Equations (ICLR 2024 · 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.