AI & Stat Mech in South Italy. From a vision of Federica Gerace Federica to reality in Roccella Ionica next September. Deadline: April 30th. Registration is free. For applications: sites.google.com/view/rockin-ai…

Not exactly thrilled but at least not unhappy to introduce single-instance Franz-Parisi, a new tool to investigate Transfer Learning in neural networks: arxiv.org/abs/2407.07168. Great collaboration with Federica, @RosalbaPacelli and Pietro Rotondo.

For all my friends who still believe in fairytales such as trickle-down economics, Santa Claus, or meritocracy: check this out mkorostoff.github.io/1-pixel-wealth/

Our paper made it to the editor's highlights of Nature Communications! We analytically investigate feature learning in overparametrized CNNs: rdcu.be/d5Rsq Riccardo Aiudi Paolo Baglioni Pietro Rotondo nature.com/collections/hj…

Our paper on the statistical mechanics of transfer learning is now published in PRL. Franz-Parisi meets Kernel Renormalization in this nice collaboration with friends in Bologna (Federica) and Parma (P. Rodondo, Rosalba Pacelli). journals.aps.org/prl/abstract/1…

It is a great pleasure to host the Workshop in Advancements in High-Dimensional Methods for Machine Learning next week at Chalmers University of Technology! We have a great set of speakers, and I look forward to the talks and discussions! 🔗 chalmers.se/en/current/cal…