Skip to content
arXiv stat.ML · Papers

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning

arXiv:2602.20062v2 Announce Type: replace-cross Abstract: Pretraining and fine-tuning are central stages in modern machine learning systems. In practice, feature learning plays an important role across both stages: deep neural networks learn a broad range of useful features during pretraining and further refine those f