A Novel CNN Ablation Reveals Limited Fourier Inductive Bias in LiteFNO: A Reproducibility Study
Goldstein, Jacob; Zhou, Kristen; Lu, Wenhao; Zhang, David J; Deshpande, Spursh; Yi, Hyunjun;
A Novel CNN Ablation Reveals Limited Fourier Inductive Bias in LiteFNO: A Reproducibility Study
We present a from-scratch reproducibility study and critical ablation of LiteFNO (Ahn et al., 2025), a lightweight Fourier Neural Operator for time-dependent PDEs. Key contributions:- From-scratch reimplementation with documented ambiguities- Parameter-matched low-rank CNN baseline (absent in original paper)- CNN matches or outperforms LiteFNO across 3 seeds on Gray-Scott (32×32)- Confirms "compact beats dense" but shows gains come from compactness, not Fourier bias Full code: https://github.com/AIscend-Research/litefno-repro