2 papers
stat.ML2026
A Theoretical Framework for LLM Fine-tuning Using Early Stopping for Non-random Initialization
Zexuan Sun, Garvesh Raskutti
In the era of large language models (LLMs), fine-tuning pretrained models has become ubiquitous. Yet the theoretical underpinning remains an open question. A central question is wh…
stat.ML2025
Reliable and scalable variable importance estimation via warm-start and early stopping
Zexuan Sun, Garvesh Raskutti
As opaque black-box predictive models become more prevalent, the need to develop interpretations for these models is of great interest. The concept of variable importance and Shapl…