Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity

Documenti analoghi

• Algorithmic Task Capture, Computational Complexity, and Inductive Bias of Infinite Transformers
  di: Davidovich, Orit, et al.
  Pubblicazione: (2026)
• Grokking as a First Order Phase Transition in Two Layer Networks
  di: Rubin, Noa, et al.
  Pubblicazione: (2023)
• From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
  di: Rubin, Noa, et al.
  Pubblicazione: (2025)
• Applications of Statistical Field Theory in Deep Learning
  di: Ringel, Zohar, et al.
  Pubblicazione: (2025)
• Demystifying Spectral Bias on Real-World Data
  di: Lavie, Itay, et al.
  Pubblicazione: (2024)