Efficient Hyperparameter Tuning via Trajectory Invariance Principle

Documenti analoghi

• On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
  di: Li, Bingrui, et al.
  Pubblicazione: (2024)
• Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
  di: Zhou, Zhanpeng, et al.
  Pubblicazione: (2024)
• Principled Architecture-aware Scaling of Hyperparameters
  di: Chen, Wuyang, et al.
  Pubblicazione: (2024)
• Efficient Backpropagation with Variance-Controlled Adaptive Sampling
  di: Wang, Ziteng, et al.
  Pubblicazione: (2024)
• Using Sequential Statistical Tests for Efficient Hyperparameter Tuning
  di: Buczak, Philip, et al.
  Pubblicazione: (2021)