Rajiv Sambharya
I am an Assistant Professor in the Industrial and Systems Engineering Department at Texas A&M University. My research lies at the intersection of optimization, control, and machine learning. I focus on developing data-driven tools to enable fast and reliable optimization. My email is rajivsambharya@tamu.edu.
Upcoming Talks
University of Delaware, Robotics Graduate Student Organization
INFORMS Annual Meeting, San Francisco
News
New preprint on Verifying Performance, Stability, and Feasibility of Inexact Non-linear Model Predictive Controllers with Sribalaji C. Anand and George Pappas. We develop an optimization framework that numerically certifies the worst-case suboptimality, closed-loop stability, and feasibility of inexact controllers for non-linear model predictive control.
I gave a talk at the Engineering Technology and Industrial Distribution Department Seminar at Texas A&M University on Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization. Thank you Jorge Alvarado and Albert Patterson for the invitation!
I began teaching DAEN429: Data Analytics II at Texas A&M, a deep learning course in the Data Engineering program.
I have started as an Assistant Professor in the Industrial and Systems Engineering Department at Texas A&M University!
Our paper Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization with Bartolomeo Stellato was accepted to the SIAM Journal on Mathematics of Data Science.
I gave a talk at the SIAM Conference on Optimization in Edinburgh on Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization. Thank you Bartolomeo Stellato for the invitation!
I organized a session called Data-Driven Algorithm Design and Analysis for Parametric Optimization at the INFORMS Optimization Society Conference in Atlanta. Thank you Mathieu Dahan for the kind invitation. In the same session, I gave a talk on Verification of Sequential Convex Programming for Parametric Non-convex Optimization.
New preprint on Verification of Sequential Convex Programming for Parametric Non-convex Optimization with Nik Matni and George Pappas. We introduce a verification framework to exactly verify the worst-case performance of sequential convex programming (SCP) algorithms for parametric non-convex optimization. Our framework provides, for the first time, global worst-case guarantees for SCP algorithms in the parametric setting.