AI Paper Atlas

Research map / Time series / Causal and generative time series

WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting

Youngin Cho, Daejin Kim, Dongmin Kim, Mohammad Azam Khan, Jaegul Choo

NeurIPS 2022 · Time series › Causal and generative time series · approach: Robust forecasting and evaluation · 2 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
add WaveBound regularizationAutoformer · ETTm2 multivariate M=96MSE: 0.262 -> 0.204Improved
add WaveBound regularizationLSTNet · ETTm2 multivariate M=96MSE: 0.455 -> 0.268Improved
add WaveBound regularizationLSTNet · ETTm2 multivariate M=96MAE: 0.511 -> 0.368Improved
add WaveBound regularizationAutoformer · ETTm2 multivariate M=720MSE: 0.446 -> 0.413Improved
add WaveBound regularizationN-BEATS · ETTm2 univariate M=96MSE: 0.073 -> 0.067Improved
add WaveBound regularizationInformer · ECL univariate M=720MSE: 0.631 -> 0.378Improved
add WaveBound regularizationInformer · Synthetic sigma=0.5MSE: 0.605 -> 0.281Improved
replace fixed-constant flooding with WaveBound (Indiv.) bounds (ablation)Autoformer · ECL M=96MSE: 0.202 -> 0.176Improved
use original flooding with a constant flood level (ablation)Autoformer · ECL M=96MSE: 0.202 -> 0.194Improved
use original flooding with a constant flood level (ablation)Informer · ECL M=96MSE: 0.335 -> 0.335No clear effect
use constant flooding per feature and time step (ablation)Pyraformer · ECL M=96MSE: 0.256 -> 0.257No clear effect
bound error individually per feature and time step instead of averaged (ablation)Informer · ECL M=96MSE: 0.302 -> 0.289Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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