When

Thursday, April 24, 2025 at 2:00 p.m.
Erfan Yazdandoost Hamedani
Assistant Professor
Systems & Industrial Engineering
University of Arizona
"Efficient Algorithms for Solving Bilevel Optimization Problems"
ENGR 301

Abstract: Bilevel optimization is an important class of hierarchical decision-making where one optimization problem is nested within another. This modeling framework finds extensive applications across diverse domains, including machine learning, energy systems, and economics. However, as the scale and complexity of these systems continue to increase, there is a critical need to develop scalable and reliable optimization algorithms for bilevel optimization.
In this talk, we discuss various bilevel-structure problems and their application in machine learning including model-agnostic meta-learning and robust multi-class classification. We then introduce novel efficient first-order algorithms with a convergence rate guarantee. We also present numerical experiments to showcase the superior performance of our methods compared with state-of-the-art methods.
Bio: Yazdandoost Hamedani is an assistant professor in the Systems and Industrial Engineering Department at the University of Arizona and a member of the applied Math and Statistics & Data Science GIDPs. He received a bachelor’s degree in mathematics and applications from the University of Tehran, Tehran, Iran, in 2015 and a PhD degree in industrial engineering and operation research with minor in statistics from Pennsylvania State University in August 2020. His research focuses on developing and analyzing algorithms for solving various optimization problems including saddle point problems, distributed optimization and bilevel optimization. His research has been supported by NSF and Arizona TRIF.