On the global convergence of gradient descent for wide shallow models with bounded nonlinearities

Documenti analoghi

• Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport
  di: Barboni, Raphaël, et al.
  Pubblicazione: (2024)
• Robust Sublinear Convergence Rates for Iterative Bregman Projections
  di: Peyré, Gabriel
  Pubblicazione: (2026)
• Curvature of optimal transport with respect to the cost and applications to inverse optimal transport
  di: Peyré, Gabriel, et al.
  Pubblicazione: (2026)
• Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks
  di: Jentzen, Arnulf, et al.
  Pubblicazione: (2024)
• Global convergence of gradient descent for phase retrieval
  di: Fougereux, Théodore, et al.
  Pubblicazione: (2024)