Zheng et al. (2024) demonstrated that autoregressively trained Transformers can implement in-context learning by learning a meta-optimizer, specifically learning to perform one-step gradient descent to solve ordinary least squares (OLS) problems under specific initial data distribution conditions.

Authors

• Person: Not available Organization: arXiv
  A Survey on the Theory and Mechanism of Large Language Models

Sources

• A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv via serper

Referenced by nodes (3)

• Transformers concept
• In-Context Learning concept
• gradient descent concept