Fast Distributed Optimization and Learning over Wireless Networks with Newton-type Methods

Next generation of networked cyber-physical  systems will support a number of application domains e.g. connected autonomous vehicular networks, collaborative robotics in smart factories, and many other mission-critical applications.

With the advent of massive machine-to-machine communication and IoT networks, huge volumes of data can be collected and processed with low latency through edge computing facilities.

Distributed machine learning  enables  cross-device  collaborative learning without exchanging raw data, ensuring privacy and reducing communication cost.

Learning over wireless networks poses significant challenges due to limited communication bandwidth and channel variability, limited computational resources at the IoT devices, the heterogeneous nature of distributed data, and also randomly time-varying network topologies.

In this project, we aim to design and analyze  fast, low-complexity communication-efficient distributed learning and optimization algorithms that are adaptive to the constraints posed by the underlying wireless networks.

The nature of this project is multi-disciplinary, requiring tools from distributed optimization and control, wireless communications and networks, signal processing, statistical machine learning and random matrix theory.

This project will advance the state-of-the-art in distributed learning over wireless networks, and also contribute to design guidelines for practical learning algorithms in connected autonomous system applications.