Search Results for author:
Found 3 papers, 0 papers with code
Locally Asynchronous Stochastic Gradient Descent for Decentralised Deep Learning
2) Asynchronous centralised algorithms with a server based topology that is prone to communication bottleneck.
An Exploration into why Output Regularization Mitigates Label Noise
In this work we aim at closing this gap by showing that losses, which incorporate an output regularization term, become symmetric as the regularization coefficient goes to infinity.
Overcoming Forgetting in Federated Learning on Non-IID Data
Building on an analogy with Lifelong Learning, we adapt a solution for catastrophic forgetting to Federated Learning.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
