Pith. sign in

REVIEW 6 cited by

Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2210.03675 v3 pith:OFG4NGDN submitted 2022-10-07 cs.LG stat.ML

Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts

classification cs.LG stat.ML
keywords timekoopmanseriesshiftsneuralchangingdeepdistribution
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs). In this paper, we propose a novel deep sequence model based on the Koopman theory for time series forecasting: Koopman Neural Forecaster (KNF) which leverages DNNs to learn the linear Koopman space and the coefficients of chosen measurement functions. KNF imposes appropriate inductive biases for improved robustness against distributional shifts, employing both a global operator to learn shared characteristics and a local operator to capture changing dynamics, as well as a specially-designed feedback loop to continuously update the learned operators over time for rapidly varying behaviors. We demonstrate that \ours{} achieves superior performance compared to the alternatives, on multiple time series datasets that are shown to suffer from distribution shifts.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction

    cs.LG 2026-06 unverdicted novelty 6.0

    Proposes feature splitting and a closed-form bound on extrapolation range to enable zero-shot topological out-of-domain generalization in dynamical systems reconstruction across tipping points.

  2. SPDM: Geometry-Modulated State Space Modeling with Manifold Constraints for Time Series Forecasting

    cs.LG 2026-06 unverdicted novelty 6.0

    SPDM is a geometry-aware state-space model that projects covariance matrices onto the SPD manifold tangent space and uses geometric gating to modulate SSM parameters for improved multivariate time series forecasting.

  3. Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction

    cs.LG 2026-05 unverdicted novelty 6.0

    GTF-DEER augments the DEER framework with Generalized Teacher Forcing to allow effective parallel training of nonlinear recurrent models on extremely long sequences, improving dynamical systems reconstruction for data...

  4. Non-stationary Diffusion For Probabilistic Time Series Forecasting

    cs.LG 2025-05 unverdicted novelty 6.0

    NsDiff combines a denoising diffusion conditional generative model with a pre-trained mean/variance estimator and an uncertainty-aware noise schedule based on the Location-Scale Noise Model to capture time-varying unc...

  5. Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

    cs.LG 2026-07 unverdicted novelty 5.0

    Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.

  6. Learning the Koopman Operator using Attention Free Transformers

    cs.LG 2026-06 unverdicted novelty 5.0

    Koopman autoencoders with attention-free latent memory and online change-point re-encoding reduce long-horizon error on Duffing, Repressilator, and IRMA benchmarks while keeping low latency.