Recurrent neural networks (RNNs) are capable of learning features and long term
dependencies from sequential and time-series data. The RNNs have a stack of non-linear …

In modern transportation, pavement is one of the most important civil infrastructures for the
movement of vehicles and pedestrians. Pavement service quality and service life are of …

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 …

Lacking of adaptation to various array imperfections is an open problem for most high-
precision direction-of-arrival (DOA) estimation methods. Machine learning-based methods …

We study local SGD (also known as parallel SGD and federated SGD), a natural and
frequently used distributed optimization method. Its theoretical foundations are currently …

We analyze Local SGD (aka parallel or federated SGD) and Minibatch SGD in the
heterogeneous distributed setting, where each machine has access to stochastic gradient …

Purpose Due to the potential risk of inducing cancer, radiation exposure by X‐ray CT
devices should be reduced for routine patient scanning. However, in low‐dose X‐ray CT …

In this paper, we propose a StochAstic Recursive grAdient algoritHm (SARAH), as well as its
practical variant SARAH+, as a novel approach to the finite-sum minimization problems …

Machine learning (ML) is a promising enabler for the fifth-generation (5G) communication
systems and beyond. By imbuing intelligence into the network edge, edge nodes can …

Distributed model training suffers from communication overheads due to frequent gradient
updates transmitted between compute nodes. To mitigate these overheads, several studies …