Emergence in non-neural models: grokking modular arithmetic via average gradient outer product

Documenti analoghi

• Quadratic models for understanding catapult dynamics of neural networks
  di: Zhu, Libin, et al.
  Pubblicazione: (2022)
• xRFM: Accurate, scalable, and interpretable feature learning models for tabular data
  di: Beaglehole, Daniel, et al.
  Pubblicazione: (2025)
• Average gradient outer product as a mechanism for deep neural collapse
  di: Beaglehole, Daniel, et al.
  Pubblicazione: (2024)
• Toward universal steering and monitoring of AI models
  di: Beaglehole, Daniel, et al.
  Pubblicazione: (2025)
• Eigenvectors of the De Bruijn Graph Laplacian: A Natural Basis for the Cut and Cycle Space
  di: Philippakis, Anthony, et al.
  Pubblicazione: (2024)