1
Efficient DP-SGD for LLMs with Randomized Clipping
面向大语言模型的高效差分隐私训练方法，提出随机裁剪机制优化DP-SGD，兼顾隐私与性能。
arXiv:2605.24879v1 Announce Type: new Abstract: Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Diff…