AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics

Koen Minartz, Yoeri Poels, Simon Martinus Koop, Vlado Menkovski

NeurIPS 2023 · Probabilistic and scientific modeling › Dynamical systems · approach: Physics-informed dynamics learning · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add equivariance (PNS to EPNS) (ablation)EPNS · Celestial dynamicsD_KS kinetic energy t=50: 0.61 -> 0.14Improved
add equivariance (PNS to EPNS) (ablation)EPNS · Celestial dynamicsD_KS kinetic energy t=100: 0.20 -> 0.14Improved
add equivariance (PNS to EPNS) (ablation)EPNS · Celestial dynamicsLL: 10.9 -> 10.8No clear effect
add equivariance (PNS to EPNS) (ablation)EPNS · Cellular dynamicsLL: -16.4 -> -5.9Improved
add equivariance (PNS to EPNS) (ablation)EPNS · Cellular dynamicsD_KS clusters t=45: 0.77 -> 0.58Improved
use EPNS instead of NSDEEPNS · Celestial dynamicsLL: -5.0 -> 10.8Improved
use EPNS instead of ODE2VAEEPNS · Cellular dynamicsLL: -30.1 -> -5.9Improved
add equivariance, equivariance check on x-coordinate (ablation)EPNS · Celestial dynamicsD_KS between transformed distributions: 0.09 -> 0.04Improved
add equivariance, equivariance check on distance traveled (ablation)EPNS · Cellular dynamicsD_KS between transformed distributions: 0.503 -> 0.036Improved
reduce training set from 800 to 80 samples (EPNS) (ablation)EPNS · Celestial dynamicstest ELBO: 10.8 -> 9.9Hurt
reduce training set from 800 to 80 samples (PNS) (ablation)PNS · Celestial dynamicstest ELBO: 10.9 -> 7.7Hurt
reduce training set from 800 to 80 samples (EPNS) (ablation)EPNS · Cellular dynamicstest ELBO: -59.4 -> -59.6No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy