Advances and open problems in federated learning
Federated learning (FL) is a machine learning setting where many clients (eg, mobile
devices or whole organizations) collaboratively train a model under the orchestration of a …
devices or whole organizations) collaboratively train a model under the orchestration of a …
Large language models can be strong differentially private learners
X Li, F Tramer, P Liang, T Hashimoto - ar** in private sgd: A geometric perspective
Deep learning models are increasingly popular in many machine learning applications
where the training data may contain sensitive information. To provide formal and rigorous …
where the training data may contain sensitive information. To provide formal and rigorous …