Federica Gerace

Probing transfer learning with a model of synthetic correlated datasets

2022 · Machine Learning Science and Technology

Abstract Transfer learning can significantly improve the sample efficiency of neural networks, by exploiting the relatedness between a data-scarce target task and a data-abundant source task. Despite years of successful applications, transfer learning practice often …

Statistical mechanics of transfer learning in fully-connected networks in the proportional limit

2024 · arXiv (Cornell University)

Transfer learning (TL) is a well-established machine learning technique to boost the generalization performance on a specific (target) task using information gained from a related (source) task, and it crucially depends on the ability of …