AI Paper Atlas

Research map / Time series / Causal and generative time series

Latent Ordinary Differential Equations for Irregularly-Sampled Time Series

NeurIPS 2019 · Time series › Causal and generative time series · approach: Neural differential equations · 238 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 RNN encoder with ODE-RNN encoder (ablation)Latent ODE · MuJoCo interpolation 10%MSE: 2.477 -> 0.360Helped
replace RNN encoder with ODE-RNN encoder (ablation)Latent ODE · PhysioNet interpolationMSE: 3.907 -> 2.118Helped
continuous ODE hidden dynamics between observations (ODE-RNN) vs RNNautoregressive RNN · MuJoCo interpolation 10%MSE: 2.454 -> 1.647Helped
ODE-RNN vs RNNautoregressive RNN · MuJoCo extrapolationMSE: 7.259 -> 13.508Hurt
ODE-based models vs GRU-Dmortality classifier · PhysioNet mortalityAUC: 0.818 -> 0.833No clear effect
add Poisson process likelihood on observation times (ablation)Latent ODE · PhysioNet mortalityAUC: 0.829 -> 0.826No clear effect
Latent ODE vs ODE-RNN classifierper-time-point classifier · Human Activityaccuracy: 0.829 -> 0.846Helped

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