Regular biography
Melanie Weber is an Assistant Professor of Applied Mathematics and of Computer Science at Harvard University's John A. Paulson School of Engineering and Applied Sciences. Her research areas include Applied Mathematics, Applied Algebra and Geometry, Data Science, Machine Learning, Numerical Analysis, Theory of Computation, Artificial Intelligence, and Computation and Society. She is affiliated with the Computer Science department and is known for her work in advancing AI and computational methods. Weber has been recognized with awards such as the Leslie Fox Prize in Numerical Analysis and has been named a Sloan Fellow for her research accomplishments.
Scholar-generated biography
Melanie Weber is a researcher at Harvard University specializing in Geometry, Machine Learning, Optimization, Networks, and AI for Science. Her work explores the intersection of geometric principles and machine learning, particularly through the use of curvature measures and optimization techniques on complex networks. She has developed methods such as Forman-Ricci curvature and geometric flows to analyze and model dynamic data. Her research also includes Riemannian optimization, nonconvex stochastic optimization, and applications in brain network analysis and relational representation learning. Weber's contributions focus on enhancing the interpretability and performance of machine learning models through geometric insights.