Nicolas Loizou

Nicolas Loizou is an Assistant Professor in the Department of Applied Mathematics and Statistics at Johns Hopkins University (JHU), with a secondary appointment in Computer Science and affiliation with the Mathematical Institute for Data Science (MINDS). He leads the Optimization and Machine Learning Lab and is part of the Data Science and AI Institute. His research focuses on large-scale optimization, machine learning, federated learning, game theory, and distributed/decentralized algorithms. He holds a PhD in Operational Research from the University of Edinburgh (2019), an MSc in Computing from Imperial College London (2015), and a BSc in Mathematics from the National and Kapodistrian University of Athens (2014).

Key achievements include the OR Society’s 2019 Doctoral Award (runner-up), IVADO Postdoctoral Fellowship, COAP 2020 Best Paper Award, and a Cisco Research Grant for developing open-source federated learning tools. His work bridges theoretical guarantees with practical applications, particularly in stochastic optimization methods like the Polyak step-size and extragradient frameworks.

Research interests span federated learning architectures, sharpness-aware minimization, and multiplayer systems in AI. He has pioneered frameworks like Locally Adaptive Federated Learning and Multiplayer Federated Learning, addressing challenges in medical imaging and distributed model training. His recent event at JHU highlighted advancements in adaptive optimization algorithms for large-scale models.

• Education: PhD (Edinburgh), MSc (Imperial College), BSc (Athens University)
• Affiliations: MINDS, Data Science Institute
• Grants: Cisco Research Gift, Catalyst Award
• Labs: Optimization and Machine Learning Lab

Recent work includes improving communication efficiency in federated systems and analyzing stochastic algorithms through control-theoretic lenses. His contributions are published in top venues, with a focus on both foundational theory and real-world impact in healthcare and distributed AI.