Samuele Cornell

Papers

Total Citations

H-Index

About

Samuele Cornell is a researcher at the forefront of combinatorial optimization, with a focused expertise in applying graph neural networks (GNNs) to solve the linear sum assignment problem—a fundamental challenge in logistics, robotics, and telecommunications. His major contributions lie in pioneering graph-based neural approaches that offer efficient heuristic solutions to these computationally intractable problems, which traditionally require infeasible computational resources even for modest scales. In his 2022 paper, "Tackling the Linear Sum Assignment Problem with Graph Neural Networks," Cornell demonstrated how GNNs can learn to approximate optimal assignments, achieving notable performance gains over classical heuristics. His follow-up 2023 work, "A Graph-Based Neural Approach to Linear Sum Assignment Problems," further refined these methods, providing a scalable framework that bridges machine learning and operations research. While his citation counts (5 and 3 respectively) reflect the nascent stage of this niche field, Cornell’s work is gaining traction as a promising alternative to exact algorithms, offering practical speed-ups for real-world applications. His research stands out for its innovative fusion of deep learning and discrete optimization, positioning him as a rising voice in AI-driven problem-solving.