Rajiv Sambharya
I am a Postdoctoral Researcher in the Electrical and Systems Engineering department at Penn hosted by George Pappas. I obtained my PhD from the Operations Research and Financial Engineering department at Princeton (2019-2024) advised by Bartolomeo Stellato. I completed my Undergraduate and Master’s degrees at UC Berkeley in Electrical Engineering and Computer Science (2013-2018) advised by Laurent El Ghaoui. My research lies at the intersection of optimization, control, and machine learning. My email is sambhar9@seas.upenn.edu.
I am on the faculty job market for the 2025–2026 hiring cycle.
I will be presenting my recent work at the INFORMS Annual Meeting 2025 in Atlanta on Tuesday, October 28, 4:15-5:30 pm, in the Machine Learning and Optimization session (Building B, Level 2, Room B208).
Research: AI for Optimization toward Fast and Reliable Data-Driven Decision-Making
I am interested in methods that use AI to design and accelerate optimization algorithms, and data-driven approaches for providing rigorous performance guarantees for optimization algorithms.
- Learning to accelerate optimization algorithms: Leveraging data from related problem instances to learn hyperparameters, step-size schedules, and warm starts that significantly speed up convergence.
- Data-driven performance guarantees for algorithms: Developing statistical and optimization-based tools to certify convergence, robustness, and generalization of both classical and learned optimization algorithms.
- Applications for real-time decision-making: Applying these ideas to autonomous systems, data science, signal processing, power grids, and operations research problems that require fast, reliable optimization under changing conditions.
