Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes

Documenti analoghi

• Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training
  di: Xiao, Frank, et al.
  Pubblicazione: (2026)
• Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff
  di: Jacot, Arthur
  Pubblicazione: (2023)
• Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
  di: Bantzis, Ioannis, et al.
  Pubblicazione: (2025)
• Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
  di: Jacot, Arthur, et al.
  Pubblicazione: (2024)
• Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
  di: Wen, Yuxiao, et al.
  Pubblicazione: (2024)