The Road Less Scheduled

Documenti analoghi

• Optimal Linear Decay Learning Rate Schedules and Further Refinements
  di: Defazio, Aaron, et al.
  Pubblicazione: (2023)
• Prodigy: An Expeditiously Adaptive Parameter-Free Learner
  di: Mishchenko, Konstantin, et al.
  Pubblicazione: (2023)
• Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion
  di: Cutkosky, Ashok, et al.
  Pubblicazione: (2023)
• DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
  di: Khaled, Ahmed, et al.
  Pubblicazione: (2023)
• General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization
  di: Ahn, Kwangjun, et al.
  Pubblicazione: (2024)