AI Paper Atlas

Research map / Time series / Causal and generative time series

Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models

Vincent LE GUEN, Nicolas THOME

NeurIPS 2019 · Time series › Causal and generative time series · approach: State-space and latent dynamics forecasting · 104 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
train with DILATE instead of MSESeq2Seq · SyntheticTDI: 17.2 -> 14.8Improved
train with DILATE instead of MSESeq2Seq · ECG5000DTW: 17.8 -> 16.1Improved
train with DILATE instead of MSESeq2Seq · ECG5000MSE: 21.2 -> 30.3Hurt
train with DILATE instead of DTW_gammaSeq2Seq · ECG5000TDI: 27.2 -> 6.59Improved
train with DILATE instead of DTW_gammaMLP/Seq2Seq · all datasetsDTWNo clear effect
disentangled shape/time terms instead of weighted-DTW tangled variant (ablation)DILATE Seq2Seq · SyntheticTDI: 17.8 -> 14.8Improved
custom backward pass instead of autodiffDILATE · prediction length 100speedup: x 35Improved
alpha -> 0 (temporal term only) (ablation)DILATE · SyntheticMSE and DTWHurt
Seq2Seq DILATE vs TT-RNN trained with MSEforecasting · TrafficMSE: 0.837 vs 1.00Hurt

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