Research talk: Differentially private fine-tuning of large language models
6We have come a long way in terms of protecting privacy when training ML models, particularly with large language models. We recently demonstrated that using differentially private stochastic gradient descent (DP-SGD) to fine-tune very large language models, such as GPT-3, is not only feasible but shows very promising results with respect to the privacy-utility tradeoff. In this talk, we highlight the challenges we have overcome over the past year and the opportunities our research enables for a range of product applications.
#MSFTResearchSummit
See related sessions in this track: https://www.microsoft.com/en-us/research/video/research-talk-differentially-private-fine-tuning-of-large-language-models/
Learn more about the 2022 Microsoft Research Summit: https://www.microsoft.com/en-us/research/event/microsoft-research-summit-2022/