Skip to content
conftrace_
2025 ICML ICML 2025

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

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

Sunny Sanyal, Hayden Prairie, Rudrajit Das, Ali Kavis, Sujay Sanghavi

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Machine Learning > Application Areas > Domain Adaptation Deep Learning > Techniques > Pretraining

Keywords

catastrophic forgetting pre-trained model sample weighting fine tuning gsm8k losses
Download PDF