← Search

Taesun Yeom

2 accepted papers

2026

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization

ICML 2026poster

Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dynamics of neural nets. While its impact has been extensively studied under the asymptotic regimes---both in training time and FLS---existing theory offer…

Cited by 0SourceScholar