Bartolomeo Stellato

Bartolomeo Stellato is an Assistant Professor at Princeton University's Department of Operations Research and Financial Engineering. He is associated faculty in Electrical and Computer Engineering and Computer Science, and affiliated with Princeton's AI, Robotics, and Center for Statistics and Machine Learning initiatives. His research bridges mathematical optimization, machine learning, and optimal control for real-time decision-making in uncertain environments.

• PhD advisors: Georgina Hall, Brandon Amos
• Key collaborators: Bart Van Parys (MIT), Jaime Fernandez Fisac (UPenn), Adrien Taylor (INRIA)

His work on Mean Robust Optimization combines robust and distributionally robust optimization through data clustering, achieving 3+ orders of magnitude speedups in portfolio optimization. He also develops learned optimizers (e.g., L2WS, GeNIOS) and OSQP, which won the Beale–Orchard-Hays Prize. Recent grants include NSF CAREER (2023) and ONR Young Investigator (2025) awards.

Article Trends: His research spans optimization verification (3/7 of 2025 articles), data-driven methods (5/7 of 2024-2025 articles), control applications (4/15 articles), and equitable resource allocation (2/15 articles). Key subfields include algorithm verification, stochastic optimization, multi-agent systems, and hardware acceleration.

• Scientific Awards: ONR Young Investigator (2025), Howard B. Wentz Award (2024), NSF CAREER (2023), ISSNAF Strazzabosco (2022)
• Students: Mentored 12+ graduate students/postdocs including Irina Wang (Wallace Fellowship), Rajiv Sambharya (Best Paper Award at JMLR), and Vinit Ranjan (co-author Mathematical Programming paper)

He leads the Princeton Optimization, Learning, and Control Workshop and collaborates with institutions like MIT, INRIA, and Los Alamos National Laboratory. His group develops open-source tools (OSQP, L2WS) with over 300,000 downloads.