Pith. sign in

REVIEW 4 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

classification cs.LGstat.ML
keywords timekoopmanseriesshiftsneuralchangingdeepdistribution
verification ladder T0 review T1 audit T2 compute T3 formal
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). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts

    cs.LG 2026-07 conditional novelty 6.0 of 10

    MetaKoopman meta-learns a Bayesian prior over Koopman operators and updates it online with recent data, improving multi-step forecasting and uncertainty estimates under distribution shift.

  2. Deep Koopman operator framework for causal discovery in nonlinear dynamical systems

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A deep Koopman framework called Kausal discovers causal direction and magnitude in nonlinear dynamical systems by comparing joint versus marginal prediction errors in learned observable spaces.

  3. A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A two-parameter nearest-neighbor recurrence, DynaBase, matches large foundation models at zero-shot dynamical-system reconstruction and unifies context parroting with chaotic dynamics as two ends of one parameter.

  4. Wavelet-based Disentangled Adaptive Normalization for Non-stationary Times Series Forecasting

    cs.LG 2025-06 conditional novelty 5.0 of 10

    WDAN uses wavelet decomposition to split series into trend and residual, normalizes them separately, and predicts future statistics to improve non-stationary time series forecasting.

Pith tools