Research map / Probabilistic and scientific modeling / Dynamical systems
Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
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 |
|---|---|---|---|
| Enforce uniform-motion equivariance | U-net · Rayleigh–Bénard convection, UM | RMSE: 2.27 -> 0.71 | Helped |
| Enforce uniform-motion equivariance | U-net · Rayleigh–Bénard convection, UM | ESE: 0.34 -> 0.14 | Helped |
| Enforce magnitude equivariance | U-net · Rayleigh–Bénard convection, Mag | RMSE: 3.59 -> 0.68 | Helped |
| Enforce magnitude equivariance | U-net · Rayleigh–Bénard convection, Mag | ESE: 0.55 -> 0.34 | Helped |
| Enforce rotational equivariance | U-net · Rayleigh–Bénard convection, Rot | RMSE: 2.78 -> 0.74 | Helped |
| Enforce rotational equivariance | U-net · Rayleigh–Bénard convection, Rot | ESE: 0.91 -> 1.16 | Hurt |
| Enforce scale equivariance | U-net · Rayleigh–Bénard convection, Scale | RMSE: 1.65 -> 0.90 | Helped |
| Enforce scale equivariance | U-net · Rayleigh–Bénard convection, Scale | ESE: 4.25 -> 0.89 | Helped |
| Enforce magnitude equivariance | U-net · Ocean currents, Test_time | RMSE: 0.70 -> 0.63 | Helped |
| Enforce rotational equivariance | U-net · Ocean currents, Test_time | ESE: 0.77 -> 0.42 | Helped |
| Enforce scale equivariance | U-net · Ocean currents, Test_domain | ESE: 0.73 -> 0.43 | Helped |
| Enforce equivariance | CNN · Heat diffusion, transformed Mag test set | RMSE: 0.103 -> 0.028 | Helped |
Closest papers by meaning
- Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution (ICML 2024 · similarity 0.87)
- Symmetries in Overparametrized Neural Networks: A Mean Field View (NeurIPS 2024 · similarity 0.87)
- Approximately Equivariant Neural Processes (NeurIPS 2024 · similarity 0.87)
- Learning Infinitesimal Generators of Continuous Symmetries from Data (NeurIPS 2024 · similarity 0.86)
- Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics (ICLR 2024 · similarity 0.86)
- SymDrift: One-Shot Generative Modeling under Symmetries (NeurIPS 2026 · 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.