Features are fate: a theory of transfer learning in high-dimensional regression

Javan Tahir; Surya Ganguli; Grant M. Rotskoff

2025 ICML ICML 2025

Features are fate: a theory of transfer learning in high-dimensional regression

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Javan Tahir, Surya Ganguli, Grant M. Rotskoff

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Machine Learning > Core Methods > Regression Deep Learning > Techniques > Pretraining

Keywords

transfer learning regression pre-trained model linear network fine tuning feature space overlap

Download PDF