AI Paper Atlas

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

Locally Regularized Neural Differential Equations: Some Black Boxes were meant to remain closed!

Avik Pal, Alan Edelman, Christopher Vincent Rackauckas

ICML 2023 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural ODE training and analysis · 2 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 uniform random time-point sampling for local error regularizationNeural ODE · MNISTPrediction Time (s / batch): 0.088 ± 0.020 -> 0.046 ± 0.002Improved
Sample regularization points from solver time pointsNeural ODE · MNISTTesting NFE: 303.559 ± 3.194 -> 182.849 ± 1.578Improved
Use local regularizationNeural ODE · Physionet 2012Prediction Time (s / batch): 0.16 ± 0.01 -> 0.09 ± 0.00Improved
Use local regularization with uniform time-point samplingLatent NODE · Physionet 2012Test Loss (× 10^-3): 3.41 ± 0.10 -> 3.64 ± 0.07Hurt
Use local regularization with uniform time-point samplingNSDE · MNISTPrediction Time (s / batch): 0.51 ± 0.07 -> 0.39 ± 0.10Improved
Use local regularization, sampling from solver time pointsNeural ODE · CIFAR10 Standard Neural ODETesting NFE: 115.315 ± 12.136 -> 81.301 ± 1.255Improved
Use local error regularizationMultiscale Neural ODE · CIFAR10 Multi-ScalePrediction Time (s / batch): 0.170 ± 0.005 -> 0.175 ± 0.019; 0.170 ± 0.005 -> 0.163 ± 0.015Mixed
Regularize solver error estimates using local sampling rather than global accumulationNeural Differential Equations · Across ODE and SDE experimentsTesting NFE: The abstract reports ×change{0.556}{0.733}.Improved
Use stiffness estimates for local regularization (ablation)Neural Differential Equations · ExperimentsperformanceHurt

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