H. Brendan McMahan
3 papers in the PaperMetrix corpus
Papers by this author
-
Learning Differentially Private Recurrent Language Models
2017 · arXiv (Cornell University)
We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of …
-
Training Production Language Models without Memorizing User Data
2020 · arXiv (Cornell University)
This paper presents the first consumer-scale next-word prediction (NWP) model trained with Federated Learning (FL) while leveraging the Differentially Private Federated Averaging (DP-FedAvg) technique. There has been prior work on building practical FL infrastructure, including …
-
Learning with User-Level Differential Privacy Under Fixed Compute Budgets
2025
We investigate practical and scalable algorithms for training machine learning models with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. Motivated by the application of large language …