Davide Murari

Davide Murari is a Research Fellow at the Department of Applied Mathematics and Theoretical Physics (DAMTP) at the University of Cambridge. His work focuses on the intersection of neural networks and dynamical systems, with an emphasis on structure preservation and numerical analysis. He holds a postdoctoral role where he explores theoretical and computational aspects of neural networks, particularly their connections to differential equations and physical systems.

His research interests include approximation theory for neural networks, structure-preserving integrators, and applications in computational mechanics and inverse problems. Collaborations involve leading institutions such as NTNU (Norway) and the Alan Turing Institute. Murari actively presents at international conferences, including ICIAM, SIAM, and SciCADE, and publishes in top-tier journals like Computer Methods in Applied Mechanics and Engineering and Physica D.

Key contributions include developing symplectic neural flows, enhancing Fourier neural operators with spatial features, and analyzing robustness in graph neural networks. His work bridges numerical mathematics and machine learning, addressing challenges in stability, accuracy, and scalability.

Murari’s academic networks span computational mathematics and machine learning communities, with a focus on advancing theoretical foundations while solving practical engineering and scientific problems.