Associate Professor · Andrew & Erna Viterbi Early Career Chair
Industrial & Systems Engineering · Computer Science
Quantitative & Computational Biology · Electrical Engineering
University of Southern California
Associate Director, USC–Meta Center for Research and Education in AI and Learning (REAL@USC)
Research Scientist (part-time), Google Research
Member, USC Machine Learning Center ·
USC Center for Systems and Control
Meisam Razaviyayn is an Associate Professor (with the Andrew and Erna Viterbi Early Career Chair) of Industrial and Systems Engineering, Computer Science, Quantitative and Computational Biology, and Electrical Engineering at the University of Southern California. He also serves as Associate Director of the USC–Meta Center for Research and Education in AI and Learning (REAL@USC) and is a part-time Research Scientist at Google Research. His research focuses on the design and study of scalable, trustworthy optimization algorithms for modern data science and machine learning applications. Prior to joining USC, he was a postdoctoral research fellow in the Department of Electrical Engineering at Stanford University and a Visiting Scientist at the Simons Institute for the Theory of Computing at UC Berkeley. He received his Ph.D. in Electrical Engineering (minor in Computer Science) from the University of Minnesota, where he also earned his M.Sc. in Mathematics. He is the recipient of the 2022 NSF CAREER Award, the 2022 Northrop Grumman Excellence in Teaching Award, the 2021 AFOSR Young Investigator Award, the 2021 3M Nontenured Faculty Award, the 2020 ICCM Best Paper Award in Mathematics, the 2019 IEEE Data Science Workshop Best Paper Award, and the 2014 IEEE Signal Processing Society Young Author Best Paper Award. He was among the 40 selected attendees of the 2023 German–American Frontiers of Engineering Symposium organized by the National Academy of Engineering, and is a silver medalist of Iran’s National Mathematics Olympiad.
Showing publications from the last few years, loaded automatically via the Semantic Scholar API. For a complete list, see Google Scholar.
Loading publications…
Graduate seminar exploring trustworthiness in machine learning through optimization, covering privacy safeguards (differentially private optimization), robustness enhancement (minimax formulations), and fairness principles. Co-taught with Vatsal Sharan.
Course website →Advanced graduate course covering optimization methods for modern machine learning, including stochastic methods, min-max optimization, and distributed algorithms.
Course page →Graduate-level course on optimization techniques for data analytics, covering linear programming, convex optimization, and applications in data science.
Course page →Undergraduate course covering probability theory, random variables, and statistical methods with engineering applications.
Course page →The Optimization for Data-Driven Science (ODDS) group focuses on designing efficient large-scale algorithms for machine learning.
Ph.D. in Industrial & Systems Engineering
B.S. Applied Mathematics, Emory University; B.S. Computer Engineering, Georgia Tech
Research interests: machine learning and large-scale optimization, particularly data-efficient and private machine learning.
Ph.D. in Computer Science (co-advised with Vatsal Sharan)
B.Tech Computer Science and AI, Indraprastha Institute of Information Technology, Delhi
Research interests: learning theory, large-scale optimization, and differential privacy.
Ph.D. in Computer Science
B.Sc. Computer Engineering, Sharif University of Technology. Silver medalist, Iran’s National Mathematical Olympiad.
Research interests: large-scale optimization, especially in developing trustworthy, privacy-preserving, and robust models.
Ph.D. in Industrial & Systems Engineering
B.S. Computer Science and Operations Research/Information Engineering, Cornell University
Research interests: machine learning and optimization, particularly large-scale optimization methods, online and adaptive algorithms, and ML systems.
Ph.D. in Industrial & Systems Engineering
B.S. and M.S. in Mathematics and Economics, New York University
Research interests: stochastic control, large-scale optimization, and differential privacy.
Ph.D. in Industrial & Systems Engineering (co-advised with Karthyek Murthy)
M.S. Operations Research, Cornell University
Research interests: online optimization, reinforcement learning, stochastic control, and applied probability.