AI Paper Atlas

Research map / Time series / Causal and generative time series

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

Yong Liu, Chenyu Li, Jianmin Wang, Mingsheng Long

NeurIPS 2023 · Time series › Causal and generative time series · approach: Probabilistic and conformal forecasting · 42 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 time-variant KP to time-invariant KP only (ablation)Koopa · ECLMSE: 0.148 -> 0.146Improved
add time-variant KP to time-invariant KP only (ablation)Koopa · ILIMSE: 2.146 -> 1.734Improved
add time-invariant KP to time-variant KPs only (ablation)Koopa · ECLMSE: 1.547 -> 0.146Improved
add time-invariant KP to time-variant KPs only (ablation)Koopa · TrafficMSE: 0.947 -> 0.419Improved
use Fourier Filter instead of high-low pass truncated filter (ablation)Koopa · TrafficMSE: 0.536 -> 0.419Improved
use Fourier Filter instead of truncated filter (ablation)Koopa · ILIMSE: 1.988 -> 1.734Improved
use time-invariant then time-variant order instead of switched branches (ablation)Koopa · ECLMSE: 0.696 -> 0.146Improved
remove reconstruction loss (Koopa predictor vs Koopman Autoencoder) (ablation)Koopa · ILIMSE: 2.189 -> 1.734Improved
remove reconstruction loss (Koopa predictor vs Koopman Autoencoder) (ablation)Koopa · ExchangeMSE: 0.129 -> 0.110Improved
add operator adaptation when scaling up forecast horizon (ablation)Koopa · ExchangeMSE: 0.214 -> 0.172Improved
add operator adaptation when scaling up horizon (ablation)Koopa · TrafficMSE: 0.709 -> 0.699Improved
use Koopa instead of PatchTSTPatchTST · ECL H=192MSE: 0.147 -> 0.156Hurt

Later papers that compared with this method

7 later accepted papers report Koopa as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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