Federated learning (FL) has been widely adopted to train machine learning models over
massive data in edge computing. Most works of FL employ pre-defined model architectures …

We carefully evaluate a number of algorithms for learning in a federated environment, and
test their utility for a variety of image classification tasks. We consider many issues that have …

Asynchronous learning protocols have regained attention lately, especially in the Federated
Learning (FL) setup, where slower clients can severely impede the learning process. Herein …

State-of-the-art training algorithms for deep learning models are based on stochastic
gradient descent (SGD). Recently, many variations have been explored: perturbing …

The interest in federated learning has surged in recent research due to its unique ability to
train a global model using privacy-secured information held locally on each client. This …

Modern advancements in large-scale machine learning would be impossible without the
paradigm of data-parallel distributed computing. Since distributed computing with large …

We study training one-hidden-layer ReLU networks in the neural tangent kernel (NTK)
regime, where the networks' biases are initialized to some constant rather than zero. We …

Recent work on the Lottery Ticket Hypothesis (LTH) shows that there exist “winning tickets”
in large neural networks. These tickets represent “sparse” versions of the full model that can …

Loss functions drive the optimization of machine learning algorithms. The choice of a loss
function can have a significant impact on the training of a model, and how the model learns …

Optimizing for reduced computational and bandwidth resources enables model training in
less-than-ideal environments and paves the way for practical and accessible AI solutions …