spectral-bias

Tag

Cards List
#spectral-bias

Architecture Shapes Transfer Specificity in Implicit Neural Representations

arXiv cs.LG · 5d ago Cached

This paper studies transfer specificity in implicit neural representations across SIREN, ReLU MLPs, and Fourier-feature MLPs, finding that transfer magnitude and specificity depend on architecture, with ReLU being more selective and SIREN reusing weights broadly. Results suggest architecture selection should consider explicit control conditions, not just transfer magnitude.

0 favorites 0 likes
#spectral-bias

Colored Noise Diffusion Sampling

Hugging Face Daily Papers · 2026-05-28 Cached

Introduces Colored Noise Sampling (CNS), a training-free stochastic solver for diffusion models that dynamically allocates energy based on frequency-dependent schedules, improving image quality metrics like FID significantly on ImageNet-256.

0 favorites 0 likes
#spectral-bias

Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models

arXiv cs.LG · 2026-05-27 Cached

This paper identifies and explains a spectral bias in reconstruction-based EEG foundation models, where embeddings over-represent aperiodic and low-frequency components while under-representing oscillatory components, especially at higher frequencies, leading to poor performance in low-resource settings.

0 favorites 0 likes
#spectral-bias

Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation

arXiv cs.LG · 2026-05-26 Cached

This paper introduces the Iterative Refinement Neural Operator (IRNO), which augments pretrained neural operators with a learned refinement module applied via fixed-point iteration to mitigate spectral bias. IRNO progressively corrects high-frequency errors, achieving up to 56% improvement on turbulent flow and showing stable extrapolation beyond the trained iteration count.

0 favorites 0 likes
#spectral-bias

Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations

arXiv cs.LG · 2026-05-14 Cached

This paper introduces the Spectral Energy Centroid (SEC) metric to analyze and improve spectral bias in implicit neural representations, demonstrating its utility for hyperparameter selection, signal complexity measurement, and cross-architecture alignment.

0 favorites 0 likes
← Back to home

Submit Feedback