frequency-decomposition

Tag

Cards List
#frequency-decomposition

When Does Frequency Decomposition Benefit Physics-Informed Neural Networks? A Preliminary Ablation Study

arXiv cs.LG · 2026-08-27 Cached

This study investigates the benefits of frequency decomposition for Physics-Informed Neural Networks (PINNs) by proposing a dual-branch, spectrally-gated architecture (DBSG-PINN). Ablation experiments on 1D PDE benchmarks indicate that frequency decomposition is most effective on spectrally complex problems, reducing error by up to 59.2%.

0 favorites 0 likes
#frequency-decomposition

Elucidating the SNR-t Bias of Diffusion Probabilistic Models

Hugging Face Daily Papers · 2026-04-17 Cached

This paper identifies a Signal-to-Noise Ratio timestep (SNR-t) bias in diffusion probabilistic models during inference, where SNR-timestep alignment from training is disrupted at inference time. The authors propose a differential correction method that decomposes samples into frequency components and corrects each separately, improving generation quality across models like IDDPM, ADM, DDIM, EDM, and FLUX with minimal computational overhead.

0 favorites 0 likes
← Back to home

Submit Feedback