- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes FCIG, a time-series forecasting framework that learns delay-coordinate representations through causal convolutions and uses Koopman regularization to encourage approximately linear latent dynamics. It retains direct multi-horizon prediction rather than relying on recursive latent-state evolution.
Critical strengths
- Provides representation analyses and ablation studies to investigate how convolutional coordinates and Koopman regularization affect predictive performance and latent dynamics.
- The method is well motivated by established theoretical foundations in delay-coordinate embedding and Koopman operator theory. In particular, the paper establishes a formal connection between causal convolutional projections and classical Hankel-SVD coordinates, providing a principled basis for learning forecasting-oriented representations.
- The paper goes beyond evaluating forecasting accuracy by examining the geometric and spectral properties of learned representations, providing insights into how predictive supervision shapes latent dynamics and improves the consistency of learned state-space representations.
Critical weaknesses
- The methodological novelty may be limited, as the framework primarily combines existing techniques, including convolutional encoders, Koopman regularization, and direct forecasting.
- The benefits of Koopman regularization are task-dependent; improved latent dynamical consistency does not always translate into better forecasting accuracy, as demonstrated by the Lorenz-63 experiments.
- Improvements over strong general-purpose baselines are often modest, and FCIG underperforms competing methods on the Traffic dataset, suggesting that its advantages are not universal.
Questions for authors
N/A
3 comments
Thanks for your feedback. I have raised my score.
Thank you for your careful review and for taking the time to reconsider your rating. We sincerely appreciate your support, which means a great deal to us.
Response to Reviewer Edqe
We thank the reviewer for recognizing the connection to delay-coordinate methods and the value of analyzing the learned representations. We have clarified the contribution and added controlled comparisons addressing the roles of coordinate learning and regularization. We hope these revisions and additional experiments help address your concerns.
W1. The contribution: forecasting-oriented coordinate learning
First, we would like to clarify what we set out to study. Our aim was to make forecasting representations more analyzable and bring dynamical coordinates into the learning process, rather than to design another prediction architecture. We therefore believe that assessing the contribution solely in terms of architectural novelty would overlook the central idea of this work.
In fact, we initially tried replacing a delay embedding with Hankel-SVD coordinates. In our early implementation, incorporating SVD into training was cumbersome and computationally demanding. The connection to causal convolution gave us a more natural way to learn delay-coordinate projections through standard neural-network operations, with Hankel-SVD included as a linear special case (Section 3.1). This changed our approach from supplying precomputed coordinates to letting forecasting supervision shape the coordinate construction itself. The stacked nonlinear encoder came later as an extension of this idea.
That is also why we use ReNF's compact, strong MLP backbone: it lets us test the coordinates without introducing a new prediction architecture at the same time. The added controls keep the downstream architecture fixed and compare fixed SVD, learnable linear, and nonlinear coordinates with KAR disabled. Across six datasets and two horizons, learning the linear projection improves both mean MSE and MAE in seven of twelve settings; nonlinear coordinates improve MSE in eleven and MAE in ten relative to fixed SVD (Appendix D.1, Table 10). These comparisons directly test the coordinate-learning idea that motivated the work.
W2. Task dependence of Koopman regularization
The Lorenz63 result actually highlights a distinction we consider important: coordinates can become more locally consistent without producing better forecasts. Understanding when a dynamical prior helps, and when it does not, is part of the question we wanted to investigate. We therefore report forecasting and geometric metrics together and discuss their disagreement explicitly (Section 4.4 and Appendix E.1).
To examine this more directly, we have added comparisons with No KAR and an identity-transition regularizer under the same forecasting architecture (Appendix D.2).
Across seven datasets and two horizons, KAR lowers mean MSE in 12/14 settings and MAE in 10/14 relative to Identity (Appendix D.2, Table 12). It also improves MidBlock KNN-FC and LTC in 11/14 settings each (Appendix D.2, Table 13). We see these results as evidence that KAR can contribute useful structure beyond simple temporal smoothing. The Lorenz63 result adds an important qualification: better geometric consistency alone is not enough to judge whether that structure helps prediction.
W3. Gains over strong baselines and the Traffic result
FCIG achieves the lowest or tied-lowest average MSE and MAE on six of the seven LTSF datasets. Relative to ReNF, it reduces both average errors on all four ETT datasets and Weather, while matching both reported averages on Electricity. These gains also extend across forecasting horizons. In our experience, this consistency across datasets and horizons is non-trivial on mature forecasting benchmarks, where strong models have closely clustered errors.
Traffic is indeed an exception to FCIG's leading LTSF results (Section 4.2, Table 1). Although we adopt ReNF's BDO strategy, the two models differ in scale, including their block counts and predictor widths. More fundamentally, FCIG forecasts in learned coordinate space (Section 3.2). The delay-coordinate construction and KAR introduce a dynamical prior into this representation, whose temporal geometry and frequency content can be explicitly analyzed (Sections 3.1, 3.3, and 4.3).
The controlled Traffic comparison at H=96 further shows that KAR improves forecasting MSE/MAE and both neighborhood metrics relative to Identity within the same architecture (Section 4.5, Table 4). This supports the value of the dynamical constraint in this setting. Taken together, our aim is to combine competitive forecasting with a structured, analyzable representation, rather than improve prediction accuracy alone.
We have revised the Introduction and Sections 3.1–3.3 and 4.5 to make this research goal and the evidence supporting it clearer.