AI Paper Atlas

Research map / Time series / Long-term forecasting

Learning Deep Time-index Models for Time Series Forecasting

Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

ICML 2023 · Time series › Long-term forecasting · approach: Attention for time series forecasting · 14 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 DeepTime instead of N-HiTSmultivariate time-series forecasting · ETTm2, horizon 96MSE: 0.176 -> 0.166Improved
Use DeepTime instead of N-HiTSmultivariate time-series forecasting · ECL, horizon 96MSE: 0.147 -> 0.137Improved
Use DeepTime instead of ETSformermultivariate time-series forecasting · Exchange, horizon 96MSE: 0.085 -> 0.081Improved
Use DeepTime instead of N-HiTSmultivariate time-series forecasting · Traffic, horizon 96MSE: 0.402 -> 0.390Improved
Use DeepTime instead of N-HiTSmultivariate time-series forecasting · Weather, horizon 96MSE: 0.158 -> 0.166Hurt
Use DeepTime instead of N-HiTSmultivariate time-series forecasting · ILI, horizon 24MSE: 1.862 -> 2.425Hurt
Replace random Fourier features with a linear input map (ablation)DeepTime · ETTm2 multivariate, horizon 96MSE: 0.166 -> 0.186Hurt
Use periodic activations instead of DeepTime's random Fourier feature backbone (ablation)DeepTime · ETTm2 multivariate, horizon 96MSE: 0.166 -> 0.236Hurt
Use an autoregressive RNN backbone (ablation)DeepTime · ETTm2 multivariate, horizon 96MSE: 0.166 -> 0.233Hurt
Add datetime features (ablation)DeepTime · ETTm2 multivariate, horizon 96MSE: 0.166 -> 0.226Hurt
Replace the closed-form ridge regressor with a gradient-trained linear layer (ablation)DeepTime · ETTm2 multivariate, horizon 96MSE: 0.166 -> 3.072Hurt
Add training an INR from scratch for each lookback window (ablation)DeepTime · ETTm2 multivariate, horizon 96MSE: 0.166 -> 0.251Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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