Frank–Wolfe and friends: a journey into projection-free optimization methods
05 Feb 2026, 14:30 — Room 322, UniGe DIBRIS/DIMA, Via Dodecaneso 35
Speaker:
Francesco Rinaldi — Università degli studi di Padova
Francesco Rinaldi — Università degli studi di Padova
Abstract:
This talk explores the use of projection-free algorithms, such as the Frank-Wolfe Method and its variants, for constrained optimization problems. We analyse both theoretical and computational properties of those methods. Additionally, we discuss some applications in, e.g., machine learning, and complex network analysis where the methods enable scalable and efficient solutions.
This talk explores the use of projection-free algorithms, such as the Frank-Wolfe Method and its variants, for constrained optimization problems. We analyse both theoretical and computational properties of those methods. Additionally, we discuss some applications in, e.g., machine learning, and complex network analysis where the methods enable scalable and efficient solutions.
Bio:
Francesco Rinaldi is a Full Professor at the Department of Mathematics “Tullio Levi-Civita” and a member of the Padova Neuroscience Center at the University of Padova. He previously served as Coordinator of the Data Science Master’s Programme at the same institution. He received his M.S. degree in Computer Engineering and his Ph.D. degree in Operations Research from Sapienza University of Rome in 2005 and 2009, respectively. He has authored over 80 publications in leading journals and conferences, including SIAM Journal on Optimization, SIAM Journal on Mathematics of Data Science, Mathematical Programming Computation, Mathematics of Operations Research, Bioinformatics, IEEE Transactions, Molecular Neurodegeneration, ICML and ICLR. He is the recipient of the COAP Best Paper Award 2024. His current research interests include optimization for big data, network science, and machine learning applications in medicine and biology.
Francesco Rinaldi is a Full Professor at the Department of Mathematics “Tullio Levi-Civita” and a member of the Padova Neuroscience Center at the University of Padova. He previously served as Coordinator of the Data Science Master’s Programme at the same institution. He received his M.S. degree in Computer Engineering and his Ph.D. degree in Operations Research from Sapienza University of Rome in 2005 and 2009, respectively. He has authored over 80 publications in leading journals and conferences, including SIAM Journal on Optimization, SIAM Journal on Mathematics of Data Science, Mathematical Programming Computation, Mathematics of Operations Research, Bioinformatics, IEEE Transactions, Molecular Neurodegeneration, ICML and ICLR. He is the recipient of the COAP Best Paper Award 2024. His current research interests include optimization for big data, network science, and machine learning applications in medicine and biology.