Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent

Documenti analoghi

• Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning
  di: Zhang, Yilang, et al.
  Pubblicazione: (2025)
• Low-Rank Adaptation Redux for Large Models
  di: Li, Bingcong, et al.
  Pubblicazione: (2026)
• RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models
  di: Zhang, Yilang, et al.
  Pubblicazione: (2025)
• Preconditioned Sharpness-Aware Minimization: Unifying Analysis and a Novel Learning Algorithm
  di: Zhang, Yilang, et al.
  Pubblicazione: (2025)
• Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation
  di: Zhang, Yilang, et al.
  Pubblicazione: (2026)