ICML Paper: How Pretraining Shapes Fine-Tuning Inductive Bias

ClementineDomi6 · x · 2026-07-08

The ICML 2026 paper "A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning" theoretically explores how pretraining shapes the inductive bias of downstream fine-tuning. It bridges the gap in the theoretical understanding of the ubiquitous pretraining+fine-tuning paradigm in modern machine learning. The paper will be presented at Poster Session 8 on July 9.

Related event: ICML Paper: How Pretraining Shapes Inductive Bias in Fine-Tuning(5 posts)→

Original post →

More from Research

Research channel →