AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Deep Energy-based Modeling of Discrete-Time Physics

Takashi Matsubara, Ai Ishikawa, Takaharu Yaguchi

NeurIPS 2020 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Probabilistic inference for ODEs and SDEs · 14 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
Train with discrete gradient (DGNet) instead of HNN++ with adaptive Dormand-Princeenergy-based PDE model · Cahn-Hilliardtime-derivative MSE (x1e0): 33.03 -> 7.14Improved
Train with discrete gradient (DGNet) instead of HNN++ with adaptive DPenergy-based PDE model · KdVenergy MSE (x1e-3): 3.01 -> 1.60Improved
Use implicit discrete-gradient prediction instead of explicit RK2 prediction (ablation)DGNet · Cahn-Hilliardenergy MSE (x1e-6): >10000 -> 0.34Improved
Use implicit discrete-gradient prediction instead of explicit RK2 prediction (ablation)DGNet · Mass-Springenergy MSE (x1e-3): 61.26 -> 0.62Improved
Use implicit scheme instead of ada. DP at prediction (ablation)DGNet · KdVenergy MSE (x1e-3): 1.60 -> 1.60No clear effect
Use DGNet instead of HNNenergy-based ODE model · Pendulumenergy MSE (x1e-3): 16.55 -> 10.79Improved
Use DGNet instead of SRNN (separable-Hamiltonian design)energy-based ODE model · 2-Bodyenergy MSE (x1e-6): 40.37 -> 81.03Hurt
Use DGNet instead of HNNenergy-based ODE model · Real Pendulumenergy MSE (x1e-3): 2.86 -> 0.50Improved
Use DGNet instead of HNNenergy-based ODE model · Mass-Springtime-derivative MSE (x1e-3): 38.22 -> 38.50No clear effect
Use higher-order adaptive integrator (ada. DP) instead of RK2 for HNN++ trainingHNN++ · Cahn-Hilliardtime-derivative MSE (x1e0): 344.23 -> 33.03Improved

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