Meisam Razaviyayn

About

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.

Research topics

• Computer Science
• Mathematics
• Mathematical optimization
• Combinatorics
• Artificial Intelligence
• Engineering
• Algorithm
• Physics
• Electrical engineering
• Mathematical analysis

Selected publications

• Nonconvex Min-Max Optimization: Applications, Challenges, and Recent Theoretical Advances

  IEEE Signal Processing Magazine · 2020 · 109 citations

  1st authorCorresponding

  The min-max optimization problem, also known as the <;i>saddle point problem<;/i>, is a classical optimization problem that is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the argument that leads to a small objective value even for the worst-case function in the given class. Min-max optimization problems have recently become very popular in a wide range of signal and data processing applications, such as fair beamforming, tr…

  DOI

• Efficient Search of First-Order Nash Equilibria in Nonconvex-Concave Smooth Min-Max Problems

  arXiv (Cornell University) · 2021 · 34 citations

  Senior authorCorresponding

  We propose an efficient algorithm for finding first-order Nash equilibria in min-max problems of the form $\min_{x \in X}\max_{y\in Y} F(x,y)$, where the objective function is smooth in both variables and concave with respect to $y$; the sets $X$ and $Y$ are convex and "projection-friendly," and $Y$ is compact. Our goal is to find an $(\varepsilon_x,\varepsilon_y)$-first-order Nash equilibrium with respect to a stationarity criterion that is stronger than the commonly used proximal gradient norm…

• A Block Successive Upper-Bound Minimization Method of Multipliers for Linearly Constrained Convex Optimization

  Mathematics of Operations Research · 2020 · 33 citations

  Consider the problem of minimizing the sum of a smooth convex function and a separable nonsmooth convex function subject to linear coupling constraints. Problems of this form arise in many contemporary applications, including signal processing, wireless networking, and smart grid provisioning. Motivated by the huge size of these applications, we propose a new class of first-order primal–dual algorithms called the block successive upper-bound minimization method of multipliers (BSUM-M) to solve t…

  DOI

• Impedimetric Sensing: An Emerging Tool for Combating the COVID-19 Pandemic

  Biosensors · 2023 · 20 citations

  The COVID-19 pandemic revealed a pressing need for the development of sensitive and low-cost point-of-care sensors for disease diagnosis. The current standard of care for COVID-19 is quantitative reverse transcriptase polymerase chain reaction (qRT-PCR). This method is sensitive, but takes time, effort, and requires specialized equipment and reagents to be performed correctly. This make it unsuitable for widespread, rapid testing and causes poor individual and policy decision-making. Rapid antig…

  DOI

• Characterizing Kupffer Cell Production of CD5 Antigen-Like and Its Function on Regulating Migration of Natural Killer T Cells

  American Journal Of Pathology · 2025-07-08 · 3 citations

  articleOpen access

  CD5 antigen-like (CD5L) is a multifunctional glycoprotein characterized for its role in the lipid metabolism, particularly within macrophages. In the liver, CD5L strongly correlates with liver injury. This study explored the role of CD5L on liver lipid accumulation and inflammatory response. CD5L promoted lipid uptake in hepatocytes and stellate cells. In multiple models of liver injury, expression of Cd5l was associated with that of Clec4f, a marker for liver macrophages, consistent with its ro…

  PublisherOA PDFDOI

Frequent coauthors

• Zhi‐Quan Luo

  47 shared

• Mingyi Hong

  43 shared

• Maziar Sanjabi

  42 shared

• Babak Barazandeh

  Splunk (United States)

  31 shared

• Maher Nouiehed

  American University of Beirut

  26 shared

• Sina Baharlouei

  26 shared

• Andrew M. Lowy

  23 shared

• Jason D. Lee

  23 shared

Labs

• ODDS Research GroupPI

  Focuses on designing efficient large-scale algorithms for machine learning.

Education

• Ph.D., Electrical Engineering (minor in Computer Science)

  University of Minnesota

• M.S., Mathematics

  University of Minnesota

Awards & honors

• 2022 NSF CAREER Award
• 2022 Northrop Grumman Excellence in Teaching Award
• 2021 AFOSR Young Investigator Award
• 2021 3M Nontenured Faculty Award
• 2020 ICCM Best Paper Award in Mathematics

Similar researchers at University of Southern California

• Carl F Kesselmanh-80
• Jong-Shi Pangh-73
• Maged M. Dessoukyh-51