Nicolas Garcia Trillos

Nicolas Garcia Trillos is an Associate Professor in the Department of Statistics at the University of Wisconsin-Madison, with research spanning applied analysis, computational probability, statistics, and machine learning. His work focuses on the intersection of calculus of variations, optimal transport, and partial differential equations in learning systems.

His educational background includes:

• Bachelor's degree in Mathematics from Universidad de Los Andes, Bogotá, Colombia (2010)
• Ph.D. in Mathematics from Carnegie Mellon University (2015)
• Prager Assistant Professor (postdoctoral position) at Brown University (2015-2018)

Garcia Trillos' research centers on the mathematical foundations of machine learning, developing tools in optimal transport and calculus of variations to analyze graph-based learning and continuum models. Key contributions address adversarial robustness, federated learning, and spectral clustering, providing theoretical guarantees for large-scale problems through PDE frameworks.

Recent publications (2022-2025) demonstrate a cohesive focus on geometric approaches to adversarial robustness, using optimal transport to derive classification bounds and study solution existence. He has advanced federated learning via consensus-based bi-level optimization (CB2O) and developed Fermat distances for metric approximation, bridging pure mathematics with statistical learning theory.

No scientific awards were mentioned in the provided text.

There is no information available regarding student advising, research grants, or laboratory affiliations in the source material.