Research map / Probabilistic and scientific modeling / Dynamical systems
Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics
Koen Minartz, Yoeri Poels, Simon Martinus Koop, Vlado Menkovski
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 |
|---|---|---|---|
| add equivariance (PNS to EPNS) (ablation) | EPNS · Celestial dynamics | D_KS kinetic energy t=50: 0.61 -> 0.14 | Improved |
| add equivariance (PNS to EPNS) (ablation) | EPNS · Celestial dynamics | D_KS kinetic energy t=100: 0.20 -> 0.14 | Improved |
| add equivariance (PNS to EPNS) (ablation) | EPNS · Celestial dynamics | LL: 10.9 -> 10.8 | No clear effect |
| add equivariance (PNS to EPNS) (ablation) | EPNS · Cellular dynamics | LL: -16.4 -> -5.9 | Improved |
| add equivariance (PNS to EPNS) (ablation) | EPNS · Cellular dynamics | D_KS clusters t=45: 0.77 -> 0.58 | Improved |
| use EPNS instead of NSDE | EPNS · Celestial dynamics | LL: -5.0 -> 10.8 | Improved |
| use EPNS instead of ODE2VAE | EPNS · Cellular dynamics | LL: -30.1 -> -5.9 | Improved |
| add equivariance, equivariance check on x-coordinate (ablation) | EPNS · Celestial dynamics | D_KS between transformed distributions: 0.09 -> 0.04 | Improved |
| add equivariance, equivariance check on distance traveled (ablation) | EPNS · Cellular dynamics | D_KS between transformed distributions: 0.503 -> 0.036 | Improved |
| reduce training set from 800 to 80 samples (EPNS) (ablation) | EPNS · Celestial dynamics | test ELBO: 10.8 -> 9.9 | Hurt |
| reduce training set from 800 to 80 samples (PNS) (ablation) | PNS · Celestial dynamics | test ELBO: 10.9 -> 7.7 | Hurt |
| reduce training set from 800 to 80 samples (EPNS) (ablation) | EPNS · Cellular dynamics | test ELBO: -59.4 -> -59.6 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ODE2VAE — ODE2VAE: Deep generative second order ODEs with Bayesian neural networks (NeurIPS 2019) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Equivariant Graph Neural Operator for Modeling 3D Dynamics (ICML 2024 · similarity 0.87)
- SymDiff: Equivariant Diffusion via Stochastic Symmetrisation (ICLR 2025 · similarity 0.86)
- Approximately Equivariant Neural Processes (NeurIPS 2024 · similarity 0.86)
- Learning (Approximately) Equivariant Networks via Constrained Optimization (NeurIPS 2025 · similarity 0.86)
- SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases (ICLR 2024 · similarity 0.85)
- Closing the Approximation Gap in Simulation-free Latent SDEs (NeurIPS 2026 · similarity 0.85)
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.
