Optimization and Learning for Communications

The Optimization and Learning for Communications (OLC) group leverages a robust theoretical understanding of wireless networks to guarantee their efficiency, reliability, and scalability. We apply state-of-the- art mathematical tools, including fixed-point theory, convex analysis, statistics, distributed optimization, and more, to address real-world signal processing and machine learning problems in wireless systems. Our focus is on developing efficient algorithms with strong theoretical guarantees that combine model-based and data-driven approaches. Our research topics include physical layer signal processing for radio access networks, network analytics, network planning, and fundamental AI research.