Simone Brugiapaglia is an Associate Professor in the Department of Mathematics and Statistics at Concordia University in Montréal, Canada. His academic journey includes a PhD in Mathematical Models and Methods from Polytechnic University of Milan (2016), an MSc in Mathematics from University of Pisa (2012), and a BSc in Mathematics from University of Pisa (2010), all earned cum laude . Prior to his current role, he held postdoctoral positions at École polytechnique fédérale de Lausanne (2016) and Simon Fraser University (2016-2019). Dr. Brugiapaglia's research bridges mathematics, data science, and computational methods. Key interests include: Foundations of deep learning and neural networks Compressed sensing and sparse recovery algorithms High-dimensional approximation theory Numerical methods for PDEs and diffusion equations Physics-informed machine learning Optimization techniques for large-scale problems His work develops rigorous mathematical frameworks for data-driven algorithms. His publications (30+ including two books) consistently focus on high-dimensional computation , featuring recent advances in neural network theory (e.g., generalization bounds, rank collapse), compressed sensing techniques (e.g., greedy algorithms, unrolled networks), and physics-informed learning. A strong trend involves combining traditional numerical methods with deep learning for PDE solutions. Awards & Fellowships: Concordia Research Fellow (2023) Leslie Fox Prize for Numerical Analysis (2nd place, 2019) PIMS Postdoctoral Fellowship (2016-2018) Multiple INdAM scholarships during graduate/undergraduate studies He has supervised over 20 trainees across postdoctoral, graduate, and undergraduate levels. While specific grants aren't detailed, his fellowship history indicates sustained research funding. No explicit research labs or teams are mentioned, but his supervision record and collaborative publications suggest active leadership in research groups focused on computational mathematics.
