AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs

Talgat Daulbaev, Alexandr Katrutsa, Larisa Markeeva, Julia Gusak, Andrzej Cichocki, Ivan Oseledets

NeurIPS 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Gradient estimation for discrete variables · 10 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
replace reverse dynamic method with interpolated activations (IRDM, N=16)neural ODE training · toy density estimation (circles)training time (s): 7874 -> 6842Improved
replace reverse dynamic method with IRDM (N=16)neural ODE training · toy density estimation (2spirals)training time (s): 9285 -> 8938Improved
replace RDM with IRDMneural ODE training · miniboone density estimationtest loss vs training timeImproved
replace RDM with IRDMneural ODE training · toy dynamical system reconstructionright-hand side evaluations: at least 10 times fewerImproved
replace RDM with IRDMvariational autoencoder · caltech, freyfacesfinal test loss and training timeNo clear effect
replace RDM with IRDMneural ODE · CIFAR10 classificationtest accuracy and training time: 0.867 test accuracyImproved
use too few Chebyshev nodes (N=4) instead of more (ablation)IRDM · toy density estimationtest lossHurt
use too many Chebyshev nodes (N=128) instead of N=16 (ablation)IRDM · pinwheel density estimationtraining time (s): 4750 -> 5574Hurt
use too many Chebyshev nodes (N=128) instead of N=16 (ablation)IRDM · circles density estimationtraining time (s): 6842 -> 8113Hurt
use barycentric Lagrange interpolation instead of piecewise-linear interpolation (ablation)IRDM · MNIST classificationtest accuracy stabilityImproved
decrease DOPRI5 tolerance (ablation)IRDM · toy 2D dynamical systemgradient errorImproved
increase number of Chebyshev nodes (ablation)IRDM · toy 2D dynamical systemgradient approximation qualityHurt

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