Two-Time-Scale Learning Dynamics: A Population View of Neural Network Training

Documenti analoghi

• Analysis of mean-field models arising from self-attention dynamics in transformer architectures with layer normalization
  di: Burger, Martin, et al.
  Pubblicazione: (2025)
• Swarm-based optimization with jumps: a kinetic BGK framework and convergence analysis
  di: Borghi, Giacomo, et al.
  Pubblicazione: (2025)
• Wasserstein convergence rates for stochastic particle approximation of Boltzmann models
  di: Borghi, Giacomo, et al.
  Pubblicazione: (2025)
• A PDE Perspective on Generative Diffusion Models
  di: Liu, Kang, et al.
  Pubblicazione: (2025)
• Learning on the Temporal Tangent Bundle for Physics-Informed Neural Networks
  di: Jamal, Adetola, et al.
  Pubblicazione: (2026)