Search Results for author:
Found 2 papers, 0 papers with code
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
Recent work has highlighted the role of initialization scale in determining the structure of the solutions that gradient methods converge to.
Holdout SGD: Byzantine Tolerant Federated Learning
HoldOut SGD first randomly selects a set of workers that use their private data in order to propose gradient updates.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
