Research map / Probabilistic and scientific modeling / Differential equations and PDEs
A shooting formulation of deep learning
François-Xavier Vialard, Roland Kwitt, Susan Wei, Marc Niethammer
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use time-dependent parameterization (dynamic) instead of time-constant parameters in UpDown (ablation) | UpDown with particles · function approximation y = x^2 + 3/(1+x^2) | test loss and network complexity | Improved |
| use static with particles instead of dynamic with particles (ablation) | UpDown with particles · function approximation y = x^2 + 3/(1+x^2) | test loss | Hurt |
| dynamic particle model versus direct models on short snippets of spiral ODE (ablation) | UpDown dynamic with particles · spiral ODE | training and validation loss | Improved |
| use dynamic (time-dependent) UpDown variants instead of static variants (ablation) | UpDown · Rotating MNIST | MSE at left-out angle | No clear effect |
| allow time-dependent parameterization (ablation) | UpDown · Rotating MNIST latent space | latent structure (qualitative PCA) | Improved |
| add particle ensemble to static model (ablation) | UpDown static · Bouncing balls | per-pixel MSE: 0.0154 -> 0.0150 | Improved |
Closest papers by meaning
- Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit (ICLR 2024 · similarity 0.87)
- Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer (ICML 2025 · similarity 0.85)
- Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks (ICLR 2024 · similarity 0.85)
- Implicit regularization of deep residual networks towards neural ODEs (ICLR 2024 · similarity 0.84)
- Feature Learning Dynamics in Infinite-Depth Neural Networks (NeurIPS 2026 · similarity 0.84)
- Layer Compression of Deep Networks with Straight Flows (AAAI 2024 · similarity 0.84)
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.
