Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules

Documenti analoghi

• A Variational Manifold Embedding Framework for Nonlinear Dimensionality Reduction
  di: Vastola, John J., et al.
  Pubblicazione: (2025)
• Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems
  di: Vastola, John J.
  Pubblicazione: (2025)
• Generalization through variance: how noise shapes inductive biases in diffusion models
  di: Vastola, John J.
  Pubblicazione: (2025)
• Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
  di: Simmons-Edler, Riley, et al.
  Pubblicazione: (2025)
• Derivatives of Stochastic Gradient Descent in parametric optimization
  di: Iutzeler, Franck, et al.
  Pubblicazione: (2024)