AI Paper Atlas

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

Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics

Avik Pal, Yingbo Ma, Viral Shah, Christopher V Rackauckas

ICML 2021 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural ODE training and analysis · 4 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 local-error regularizationNeural ODE · MNISTprediction time: 0.094 $\pm$ 0.010 -> 0.060 $\pm$ 0.001Improved
add stiffness regularization (ablation)Neural ODE · MNISTprediction time: 0.094 $\pm$ 0.010 -> 0.094 $\pm$ 0.003No clear effect
combine stiffness and local-error regularization (ablation)Neural ODE · MNISTprediction time: 0.094 $\pm$ 0.010 -> 0.081 $\pm$ 0.006Improved
add local-error regularizationLatent ODE · PhysioNet 2012training time: 1.75 $\pm$ 0.39 -> 0.94 $\pm$ 0.13Improved
add stiffness regularization (ablation)Latent ODE · PhysioNet 2012prediction time: 0.53 $\pm$ 0.12 -> 0.20 $\pm$ 0.01Improved
replace the local-error penalty with squared error estimates (ablation)Latent ODE · PhysioNet 2012test resultsNo clear effect
add local-error regularizationNeural SDE · Spiral SDEtraining time: 178.95 $\pm$ 20.22 -> 173.43 $\pm$ 04.18Improved
add stiffness regularization (ablation)Neural SDE · Spiral SDEprediction time: 0.07553 $\pm$ 0.0186 -> 0.07250 $\pm$ 0.0017Improved
add local-error regularizationNeural SDE · MNISTprediction time: 15.07 $\pm$ 0.93 -> 07.23 $\pm$ 0.14Improved
add stiffness regularization (ablation)Neural SDE · MNISTtraining time: 6.32 $\pm$ 0.19 -> 8.54 $\pm$ 0.37Hurt
use higher-order derivative regularizationNeural ODE · PhysioNet 2012training time: 1.75 $\pm$ 0.39 -> 12.3 $\pm$ 0.32Hurt

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