Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
Jan 1, 2026·
,
·
0 min read
Alexander Yukhimchuk
Mladen Kolar
Martin Takáč
Sayantan Choudhury
Authors
Professor of Data Sciences and Operations
Mladen Kolar is a Professor of Data Sciences and Operations at the University of Southern California Marshall School of Business and a Visiting Professor of Statistics and Data Science at Mohamed bin Zayed University of Artificial Intelligence. Before joining USC, he was on the faculty of the University of Chicago Booth School of Business. His research is focused on high-dimensional statistical methods, graphical models, varying-coefficient models and data mining, driven by the need to uncover interesting and scientifically meaningful structures from observational data. He is a Fellow of the Institute of Mathematical Statistics.
Authors
Post-doc (2025-2026)
Sayantan Choudhury was a postdoctoral researcher at Mohamed bin Zayed University of Artificial Intelligence, hosted by Martin Takáč and Mladen Kolar. He received his PhD in Applied Mathematics and Statistics from Johns Hopkins University. His research is in machine learning and optimization, including large-scale and adaptive optimization, federated learning, and min-max problems.