- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This article investigates how temporal autocorrelation affects the spectral bias of Kolmogorov Arnold Networks (KANs) in time series forecasting. By analyzing the dominant order of the Hessian matrix, the input autocorrelation, optimization conditions, and difficulties in learning frequency dependence were linked. The author further proposed DCT-KAN, which combines discrete cosine transform preprocessing and coordinate standardization. Extensive synthesis experiments have shown that under correlated inputs, this method can better recover challenging frequency components.
Critical strengths
-
The paper investigates how temporal autocorrelation affects the optimization behavior of KANs, extending existing spectral-bias analysis beyond the independent-input setting.
-
The authors provide extensive synthetic experiments, including frequency-direction comparisons, multiple random seeds, and explicit Hessian calculations, which offer useful evidence for the proposed mechanism.
Critical weaknesses
-
All experiments utilize synthetic datasets. Without benchmarking against real-world predictions, the generalizability is questionable.
-
The main analysis relies on a transfer approximation of covariance, and the accuracy of this approximation decreases with finer spline resolutions.
-
The images and text in the paper heavily rely on AI, and should be carefully revised to enhance readability.
-
There are multiple 1-2 words occupying a line in the article (such as line 100, 107, 168, 215, 290, 421, 431, etc.), which need to be adjusted and modified.
Questions for authors
See weaknesses