Lorenzo Sabug Jr

Lorenzo Sabug Jr is a Research Associate in the Department of Electrical and Electronic Engineering at Imperial College London's Faculty of Engineering. He currently serves as co-investigator for the EPSRC-funded grant 'Concurrent Learning and Control of Large-Scale Phenomena', collaborating with Prof. Eric Kerrigan and Prof. Guillermo Rein on methodological research in physics-informed machine learning and dual control.

His educational background includes:

• Ph.D. (cum laude) in Information Engineering from Politecnico di Milano, Italy (2023)
• M.Sc. in Electrical Engineering, Information Technology, and Computer Engineering from RWTH Aachen University, Germany (2016)
• B.Sc. in Computer Engineering from University of the Philippines Diliman, Philippines (2012)

Lorenzo's research centers on the intersection of physics-informed machine learning and predictive control, with particular expertise in black-box optimization techniques. His work bridges theoretical developments with practical applications across diverse engineering domains, from emergency response to environmental phenomena like wildfires to spacecraft design and power grid management.

His methodological contributions focus on the Set Membership Global Optimization (SMGO) framework and its variants, which address optimization problems where objective functions and constraints cannot be expressed analytically. This approach has proven valuable for experimental design and simulation-based engineering applications where traditional analytical methods fail.

Lorenzo's publication record demonstrates consistent advancement from foundational optimization theory toward integrated learning-control frameworks. His work spans multiple engineering disciplines while maintaining a core focus on solving complex design problems through innovative optimization techniques when analytical solutions are not feasible. Recent publications emphasize contextual optimization and physics-informed approaches, showing evolution toward more sophisticated integration of physical models with data-driven methods.

Key achievements include:

• Development of the SMGO and SMGO-Δ optimization frameworks as open-source toolboxes
• Application of optimization techniques to spacecraft attitude control, induction heating systems, and power grid management
• Being named co-investigator for the EPSRC-funded grant 'Concurrent Learning and Control of Large-Scale Phenomena'

Lorenzo serves as an occasional reviewer for prestigious journals including Automatica, International Journal of Control, and IEEE Control Systems Society publications. He actively mentors graduate students through formal programs like the Graduate Mentorship and Assistance Program (GradMAP Philippines) and in personal capacity, guiding the next generation of researchers in optimization and control theory.