Lorenzo Rosasco
Professor University of Genova & Principal Investigator IIT
IAS SEMINAR #21/2026
Turin / OGR / Mezzanino / November 19, 2026 / 04:00 – 06:00 pm CET
A shallow story about sustainable AI
EVENT&WEBINAR
Deep networks with billions of parameters, trained on vast datasets, power AI tools that are transforming technology, science, and society at large. Yet their data and computational requirements increasingly concentrate development in the hands of a few actors, potentially limiting broader adoption. Moreover, state-of-the-art methods often rely on brute force and extensive trial and error, possibly at the expense of robustness and reliability.
But when do we need large, deep networks?
Across the landscape of problems that AI can address, datasets vary widely in size and dimension. We will show that, in moderate dimensions, classical machine learning approaches such as kernel methods can be made efficient and accurate while retaining strong theoretical guarantees. In intermediate dimensions, they can be combined with pretrained networks to achieve competitive results at lower computational cost. Finally, we will discuss theoretical results that shed light on when and why depth matters for high-dimensional problems.
LORENZO ROSASCO
Lorenzo Rosasco is a professor at the University of Genova and a principal investigator at the Italian Institute of Technology (IIT). He is a founder and coordinator of the Machine Learning Genova Center (MaLGa) and the Laboratory for Computational and Statistical Learning. He leads the Sustainable Artificial Intelligence and Learning unit at IIT. His research focuses on developing efficient machine-learning methods with rigorous theoretical foundations. He received his PhD from the University of Genova in 2006, after holding visiting positions at MIT, the Toyota Technological Institute at Chicago, and the Johann Radon Institute. From 2006 to 2013, he was a postdoctoral fellow and research scientist in MIT’s Department of Brain and Cognitive Sciences. He is an ELLIS Fellow and co-director of both the ELLIS program “Theory, Algorithms and Computations of Modern Learning Systems” and the ELLIS Genoa Unit. He has received several awards, including an ERC Consolidator Grant.
In collaboration with:
Register for In-Person Attendance
Joining us in person offers the opportunity for direct networking and interaction with both speakers and participants.
Please complete the form below to reserve your seat.
By clicking, you will be automatically registered for the in-person event.
Note: If you see a message saying you’re already subscribed, please ignore it — your in-person registration will still be confirmed.
Please note that, by attending, you implicitly authorize AI4I to film and photograph the audience during the seminar. By submitting your registration, you acknowledge and accept the AI4I Data Privacy Policy. Seats are limited: if you are unable to attend, we kindly ask you to inform us as soon as possible at ias@ai4i.it
LINK ZOOM
