AI Paper Atlas

Research map / Time series / Long-term forecasting

Reviving Error Correction in Modern Deep Time-Series Forecasting

Minh Hoang Nguyen, Van Dai Do, Huu Hiep Nguyen, Dung Nguyen, Kien Do, Hung Le

ICML 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 0 citations (OpenAlex)

Read the paper

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
add UEC-STD error corrector to autoregressive backbonesAR forecasters (TimeMixer, TimesNet, TimeXer) · Seven common datasetsMSE: 2.32%Improved
add UEC-STD to autoregressive backbonesAR forecasters · Monash datasetsMSE: 10.05%Improved
use UEC-STD instead of UEC-MLP correctorAR forecasters · ETTm2MSE error reduction (%): -2.71 -> -4.23Improved
use LSTM corrector instead of no correctionAR forecasters · ETTm2MSE error reduction (%): 0.00 -> 16.64Hurt
use tree/logistic classical correctors on large datasetsAR forecasters · Traffic and Electricitytraining convergenceHurt
add trend and seasonal inputs only (no STD output) (ablation)UEC corrector · ETTh1MSE: 0.451 -> 0.446Improved
add seasonal output to trend-only output (ablation)UEC-STD · ETTh1MSE: 0.464 -> 0.424Improved
add trend output to seasonal-only output (ablation)UEC-STD · ETTh1MSE: 0.427 -> 0.424Improved
add full STD input and output to plain corrector (ablation)UEC · TrafficMSE: 0.545 -> 0.543No clear effect
add full STD input and output to plain corrector (ablation)UEC · WeatherMSE: 0.241 -> 0.239Improved
use balanced beta validation (mix training data) instead of validation-only (ablation)UEC-STD on TimesNet · ETTh1MSE: 0.505 -> 0.450Improved
use balanced beta validation instead of validation-only (ablation)UEC-STD · ETTh1 and Weather, two backbonesMSE/MAE: 6/8 settingsImproved

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