Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Deep learning›Koopa: Koopman Predictors for Non-stationary Time Series
Machine learningTime-series forecasting

Koopa: Koopman Predictors for Non-stationary Time Series

Koopa (Koopman Predictors for Non-stationary Dynamics) · Also known as: Koopman Predictor, Koopman-based Time-Series Model, Koopa Forecaster, Koopman Tahmincisi

Koopa is a deep learning model for time-series forecasting introduced by Yong Liu, Chang Li, Jianmin Wang, and Mingsheng Long at NeurIPS 2023. It addresses the challenge of non-stationarity by disentangling time series into stationary and non-stationary components, then modeling the non-stationary dynamics using a learned approximation of the Koopman operator — a mathematical framework that lifts nonlinear systems into a linear space for tractable long-horizon prediction.

ScholarGate
  1. Machine learning
  2. v1
  3. 1 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Koopa
DLinearNon-stationary Transform…State Space Model

When to use it

Koopa is well-suited for multivariate long-horizon time-series forecasting tasks where the data exhibits clear non-stationarity — shifting means, variances, or seasonal patterns over time. It assumes that dynamics in a lifted feature space can be reasonably approximated as linear, which holds for many real-world signals such as energy, weather, and financial series. It may underperform on series with highly irregular or chaotic dynamics where no approximately linear lifting exists. Alternatives include PatchTST (patch-based attention), DLinear (direct linear baseline), or state-space models when Koopman's linearity assumption is too restrictive.

Strengths & limitations

Strengths
  • Explicitly handles non-stationarity through a principled decomposition rather than relying on normalization heuristics
  • Koopman-based linearization enables efficient multi-step forecasting without iterative error accumulation
  • Theoretically grounded in dynamical systems theory, offering interpretable latent dynamics
  • Computationally lighter than full attention-based transformers while remaining competitive on standard benchmarks
Limitations
  • The linear Koopman approximation may be insufficient for highly chaotic or irregular time series where no finite-dimensional linear lifting exists
  • Performance depends on the quality of the trend-residual decomposition, which can fail when non-stationarity is abrupt or structural breaks occur
  • The latent observable space dimension is a sensitive hyperparameter requiring careful tuning
  • Less explored in low-data regimes compared to classical statistical models; may overfit on short series

Frequently asked

How does Koopa differ from Transformer-based forecasting models like Autoformer or FEDformer?

Transformer-based models rely on attention mechanisms to capture temporal dependencies but implicitly assume approximate stationarity. Koopa explicitly decomposes the series into stationary and non-stationary parts and models the non-stationary dynamics using a Koopman operator, providing a theoretically grounded mechanism for handling distribution shift without the quadratic complexity of full self-attention.

Is the Koopman operator actually learned, and how is it parameterized?

Yes. Koopa parameterizes the Koopman operator as a learnable matrix (or low-rank factorization) within the model. An MLP encoder lifts observations into the latent observable space, and the operator is trained end-to-end with the rest of the network using standard gradient descent on the forecasting loss.

Can Koopa handle multivariate time series?

Yes. The paper demonstrates Koopa on standard multivariate benchmarks. Each variate's dynamics can be modeled jointly in the lifted space, though the specific channel-mixing strategy and whether the Koopman operator is shared or per-channel are architectural choices that affect both capacity and generalization.

Sources

  1. Liu, Y., Li, C., Wang, J., & Long, M. (2023). Koopa: Learning non-stationary time series dynamics with Koopman predictors. NeurIPS. link ↗

How to cite this page

ScholarGate. (2026, June 2). Koopa (Koopman Predictors for Non-stationary Dynamics). ScholarGate. https://scholargate.app/en/deep-learning/koopa

Related methods

DLinearNon-stationary TransformerState Space Model

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • DLinearDeep learning↔ compare
  • Non-stationary TransformerDeep learning↔ compare
  • State Space ModelEconometrics↔ compare
Compare side by side →

Similar methods

Non-stationary TransformerAutoformerTimeMixerDLinearCrossformerTSMixerETSformerPatchTST

Related reference concepts

Convolutional and Sequence ModelsDeep Generative ModelsSequence-to-Sequence Models and TransformersSelf-Supervised and Representation LearningGaussian Process ModelsDeep Learning

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Koopa (Koopa (Koopman Predictors for Non-stationary Dynamics)). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/koopa · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Yong Liu et al.
Year
2023
Type
Koopman operator-based time-series forecasting model
Subfamily
Time-series forecasting
Venue
NeurIPS 2023
Learning Paradigm
Supervised deep learning
Related methods
DLinearNon-stationary TransformerState Space Model
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account