AI Paper Atlas

Research map / Time series / Causal and generative time series

Homotopy-based training of NeuralODEs for accurate dynamics discovery

Joon-Hyuk Ko, Hankyul Koh, Nojun Park, Wonho Jhe

NeurIPS 2023 · Time series › Causal and generative time series · approach: Neural differential equations · 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
use homotopy training instead of vanilla gradient descentNeuralODE · Lotka-Volterra Black Boxinterpolation MSE (x1e-2): 1.76 -> 0.78Improved
use homotopy training instead of vanilla gradient descentNeuralODE · Lotka-Volterra Gray Boxinterpolation MSE (x1e-2): 27.3 -> 0.72Improved
use homotopy training instead of vanilla gradient descentNeuralODE · Double Pendulum Second Orderinterpolation MSE (x1e-2): 1.03 -> 0.18Improved
use homotopy training instead of vanilla gradient descentNeuralODE · Lorenz Black Boxinterpolation MSE (x1e-2): 259 -> 18.6Improved
use multiple shooting instead of homotopyNeuralODE · Lorenz Black Boxinterpolation MSE (x1e-2): 18.6 -> 12.9Mixed
use multiple shooting instead of vanilla for extrapolationNeuralODE · Double Pendulumextrapolation MSEHurt
use homotopy training instead of vanillaNeuralODE · all benchmarksepochs to minimum interpolation MSE: 90%-40% reductionImproved
use homotopy training instead of vanillaNeuralODE · Lotka-Volterra Black Boxbest train epochs: (3932, 3818, 3134) -> (299, 208, 227)Improved
increase training data length (ablation)vanilla gradient descent · Lotka-Volterrainterpolation/extrapolation MSEHurt
increase data length (ablation)homotopy and multiple shooting · Lotka-VolterraMSENo clear effect
decrease model size with homotopy or multiple shooting (ablation)NeuralODE · Lotka-VolterraMSENo clear effect
increase data sparsity and noise (ablation)homotopy training · Lotka-VolterraMSENo clear effect

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