AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints

Marc Finzi, Ke Alexander Wang, Andrew G Wilson

NeurIPS 2020 · Probabilistic and scientific modeling › Dynamical systems · approach: Physics-informed dynamics learning · 19 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
Use Cartesian coordinates with explicit constraints instead of generalized coordinates with implicit constraintsCHNN and CLNN · Physical-system benchmarkstrajectory prediction accuracy: 10 to 100 times more accurateImproved
Use Cartesian coordinates with explicit constraintsCHNN and CLNN · 2-pendulumgeometric average relative error: 20 trajectories; HNN: 200 trajectories; NeuralODE: 1600 trajectoriesImproved
Use Cartesian coordinates with explicit constraintsCHNN and CLNN · Gyroscopetrajectory prediction accuracy: 100 times more data efficient or 260 times more accurateImproved
Use Cartesian coordinates with explicit constraintsCHNN and CLNN · N-pendulum systemsgeometric mean relative errorImproved
Use Cartesian coordinates with explicit constraintsCHNN and CLNN · 3D systemsgeometric mean relative errorImproved
Use Cartesian coordinates with explicit constraintsCHNN and CLNN · Physical-system benchmarksdata efficiency: 100 times less dataImproved
Remove explicit constraints from the Cartesian-coordinate model (ablation)CHNN and CLNN · 3-Pendulumgeometric mean relative errorHurt
Remove distance constraints successively, starting from the bottom (ablation)CHNN and CLNN · 3-Pendulumgeometric mean relative error: >100 times better than HNN; removing even a single constraint makes performance slightly worse than HNNHurt
Use Cartesian coordinates rather than generalized coordinatesCHNN · N-Pendulumeffective dimensionalityImproved

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