#machine learning
Sep 2026
Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks
It is shown how pretrained information reshapes the implicit bias and training dynamics, and can thereby reduce the sample complexity of recovering the target parameters and support, by gradient-based fine-tuning.
A.-E. Decleves, Etienne Boursier, Nicolas Flammarion
· arXiv.org · 0 citations