Search Results for author:
Found 2 papers, 0 papers with code
Group Personalized Federated Learning
Federated learning (FL) can help promote data privacy by training a shared model in a de-centralized manner on the physical devices of clients.
On the geometry of generalization and memorization in deep neural networks
Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
