The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity

Documenti analoghi

• Quotient Geometry, Effective Curvature, and Implicit Bias in Simple Shallow Neural Networks
  di: Dong, Hang-Cheng, et al.
  Pubblicazione: (2026)
• Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
  di: Fang, Ronglong, et al.
  Pubblicazione: (2024)
• Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks
  di: Lei, Yunwen, et al.
  Pubblicazione: (2026)
• SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
  di: Xie, Qihu, et al.
  Pubblicazione: (2025)
• Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing
  di: Chu, Hong T. M., et al.
  Pubblicazione: (2024)