DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation

Documenti analoghi

• State Contamination in Memory-Augmented LLM Agents
  di: Wang, Yian, et al.
  Pubblicazione: (2026)
• On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
  di: Ebrahimpour-Boroojeny, Ali, et al.
  Pubblicazione: (2025)
• Increasing Both Batch Size and Learning Rate Accelerates Stochastic Gradient Descent
  di: Umeda, Hikaru, et al.
  Pubblicazione: (2024)
• Diversified Batch Selection for Training Acceleration
  di: Hong, Feng, et al.
  Pubblicazione: (2024)
• LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles
  di: Ebrahimpour-Boroojeny, Ali, et al.
  Pubblicazione: (2024)