Non-Vacuous Generalization Bounds for Large Language Models

Documenti analoghi

• Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
  di: Lotfi, Sanae, et al.
  Pubblicazione: (2024)
• Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
  di: Marek, Martin, et al.
  Pubblicazione: (2025)
• The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
  di: Goldblum, Micah, et al.
  Pubblicazione: (2023)
• The Lie Derivative for Measuring Learned Equivariance
  di: Gruver, Nate, et al.
  Pubblicazione: (2022)
• Compute Better Spent: Replacing Dense Layers with Structured Matrices
  di: Qiu, Shikai, et al.
  Pubblicazione: (2024)