Mateo Díaz is an assistant professor in the Department of Applied Mathematics and Statistics. His interests encompass continuous optimization, computation, and statistics, with a particular focus on designing and analyzing highly effective, large-scale algorithms for applications in data science, machine learning, operations research, and signal processing.
Diaz and his team received the Beale—Orchard-Hays Prize for Excellence in Computational Mathematical Programming in 2024, which recognized the team’s groundbreaking research in Primal-Dual Linear Programming.
Before his time as a postdoctoral scholar at Caltech, he received a PhD in applied mathematics and an MSc in computer science from Cornell University, mentored by Damek Davis. During his doctoral studies, he worked as a student researcher at Rappi (Colombia) and Google Research. Díaz obtained two undergraduate degrees in mathematics and in systems and computing engineering from Universidad de los Andes (Colombia).
-
Assistant Professor Mateo Diaz and his team win the 2024 Beale—Orchard-Hays Prize for their work on Primal-Dual Linear Programming.
-
Breaking dimensional limits in AI
CategoriesJohns Hopkins team develops a dimension-agnostic method for machine learning.
-
Mateo Díaz, new assistant professor in the Department of Mathematics and Statistics at Johns Hopkins, discusses his background, research interests, and enthusiasm for joining the university. Originally from Colombia, Díaz's research focuses on the intersection of continuous optimization, geometry, and statistics, with applications in data science and machine learning. In this Q&A, he shares insights into his research, real-world applications, and what drew him to this field.