The pretraining error of Large Language Models (LLMs) is decomposed into generalization error and approximation error, where the generalization error is upper bounded via the PAC-Bayes framework.

Authors

• Person: Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche Organization: AISTATS
  Track: Poster Session 3 - aistats 2026

Sources

• Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS via serper

Referenced by nodes (1)

• Large Language Models concept