Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws

Documenti analoghi

• Pruning is Optimal for Learning Sparse Features in High-Dimensions
  di: Vural, Nuri Mert, et al.
  Pubblicazione: (2024)
• Emergence and scaling laws in SGD learning of shallow neural networks
  di: Ren, Yunwei, et al.
  Pubblicazione: (2025)
• Learning to Recall with Transformers Beyond Orthogonal Embeddings
  di: Vural, Nuri Mert, et al.
  Pubblicazione: (2026)
• Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
  di: Mousavi-Hosseini, Alireza, et al.
  Pubblicazione: (2024)
• From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
  di: Tsiolis, Konstantinos Christopher, et al.
  Pubblicazione: (2025)