Brian Anderson Bullins

Brian Anderson Bullins is an Assistant Professor in the Department of Computer Science at Purdue University, affiliated with the College of Science. He previously served as a research assistant professor at the Toyota Technological Institute at Chicago (TTIC). His research focuses on optimization for machine learning, including matrix estimation techniques, higher-order methods for convex/nonconvex optimization, and distributed optimization. His work has been recognized with awards such as the Best Paper Award at COLT 2021.

Education: PhD in Computer Science from Princeton University (2019), advised by Elad Hazan. B.S. in Computer Science and Mathematics from Duke University as a Benjamin N. Duke Scholar. His research explores theoretical and practical aspects of optimization, with applications in machine learning and distributed systems.

Teaching includes courses like CS57100 (Artificial Intelligence) and CS47100 (Introduction to AI), emphasizing foundational methods in search, probabilistic reasoning, reinforcement learning, and ethical AI considerations. He has also contributed to curriculum development for data engineering courses.

Awards include the Siebel Scholarship for his doctoral research and the 2018 INFORMS Optimization Society Student Paper Prize. His recent work addresses acceleration techniques for steepest descent, lower bounds in optimization, and robust model immunization strategies.