Large language models have consistently demonstrated remarkable performance across a
wide spectrum of applications. Nonetheless, the deployment of these models can …

Pre-training exploits public datasets to pre-train an advanced machine learning model, so
that the model can be easily tuned to adapt to various downstream tasks. Pre-training has …

Public pretraining is a promising approach to improve differentially private model training.
However, recent work has noted that many positive research results studying this paradigm …

Abstract Machine learning (ML) generally performs well when there is unfettered access to
large quantities of clean, relevant data. However, harnessing the benefits of large, clean …

Large language models have repeatedly shown outstanding performance across diverse
applications. However, deploying these models can inadvertently risk user privacy. The …

Differentially private (DP) mean estimation is arguably the most comprehensively studied
problems in the DP literature, leading to various efficient estimators that achieve optimal …