Summary
Matthew Drnevich is a research physicist and PhD candidate at NYU with a decade of experience applying machine learning to experimental particle physics, currently leading simulation-based ML efforts for the ATLAS Collaboration. His work specializes in density ratio estimation and its practical uses across inference, reweighting, importance sampling, hypothesis testing, transfer learning, domain adaptation, and outlier detection. He has driven novel model architectures and loss formulations—work published on arXiv and developed during a HiDA fellowship at DESY—to address challenges like negatively weighted datasets. Matthew pairs rigorous mathematical training in honors math and physics from Notre Dame with hands-on software and data-science engineering (from internships at NASA to collaborative CMS projects). He is comfortable moving ideas from research to production-grade analysis pipelines, optimizing model diagnostics and performance on large experimental datasets. Colleagues rely on him for bridging theoretical statistical methods with practical solutions that improve physics measurements.
10 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Experimental Particle Physics, Doctor of Philosophy - PhD, Experimental Particle Physics at New York University
Bachelor’s Degree, Honors Mathematics and Physics with Honors and an Advanced Physics concentration, Bachelor’s Degree, Honors Mathematics and Physics with Honors and an Advanced Physics concentration at University of Notre Dame
High School, High School at Clear Lake High School
English, French