About Francesco Orabona Francesco Orabona Associate Professor, Computer Science Online learning optimization machine learning Statistical learning theory Achieving "parameter-free" machine learning is the primary focus of Professor Francesco Orabona. He is particularly interested in designing superior algorithms to train deep learning models. Events Presented Events Oct 4 - Oct 10, 2026 Last-Iterate Convergence of Optimistic Multiplicative Weights Update Francesco Orabona, Associate Professor, Computer Science Oct 5, 12:00 - 13:00 B9 R2325 gradient descent operation optimistic gradient descent ascent convex optimization saddle-point problems This talk will show how OMWU converges asymptotically for smooth convex-concave saddle-point problems, with a small enough constant learning rate. Sep 3 - Sep 9, 2023 Universal Portfolio Algorithm and Confidence Sequences Francesco Orabona, Associate Professor, Computer Science Sep 5, 16:00 - 17:00 B5 L5 R5209 Universal Portfolio algorithm In this talk, I will describe a surprising application for a known online learning problem and its optimal algorithm.
Last-Iterate Convergence of Optimistic Multiplicative Weights Update Francesco Orabona, Associate Professor, Computer Science Oct 5, 12:00 - 13:00 B9 R2325 gradient descent operation optimistic gradient descent ascent convex optimization saddle-point problems This talk will show how OMWU converges asymptotically for smooth convex-concave saddle-point problems, with a small enough constant learning rate.
Universal Portfolio Algorithm and Confidence Sequences Francesco Orabona, Associate Professor, Computer Science Sep 5, 16:00 - 17:00 B5 L5 R5209 Universal Portfolio algorithm In this talk, I will describe a surprising application for a known online learning problem and its optimal algorithm.
Engage KAUST Academic Portal ORCID ShareClipboard Related Sites Computer Science (CS) Center of Excellence for Generative AI (GenAI) Adaptive Machine Learning (AdaML) Related Content Articles 1 Events 2 Related Links Google Scholar Personal Website
