On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning

Documenti analoghi

• Towards Guided Descent: Optimization Algorithms for Training Neural Networks At Scale
  di: Nagwekar, Ansh
  Pubblicazione: (2025)
• Asymptotics of Linear Regression with Linearly Dependent Data
  di: Moniri, Behrad, et al.
  Pubblicazione: (2024)
• Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
  di: Moniri, Behrad, et al.
  Pubblicazione: (2026)
• On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
  di: Moniri, Behrad, et al.
  Pubblicazione: (2025)
• Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models
  di: Moniri, Behrad, et al.
  Pubblicazione: (2024)