Conceptual Challenges in AI: from ML to Average-Case Computation and Cryptography

We are pleased to highlight that an interdisciplinary workshop was held at Bocconi University from May 20 to May 24, 2024. The workshop focused on advancing dialogue between the fields of artificial intelligence, cryptography, average-case complexity, and statistical physics. The event aimed to foster collaboration by bringing together experts from these diverse domains to share current research and build new bridges across areas of growing overlap.
The program featured a varied lineup of talks, covering topics such as learning dynamics in neural networks, hardness evidence for random optimization problems, and cryptographic applications of computational intractability.
The workshop was co-organized as part of the Physics and Machine Learning research pillar of the European Laboratory for Learning and Intelligent Systems (ELLIS) and the CIFRA Institute. Organizers included Nicolas Brunel, Chris Jones, Bert Kappen, Carlo Lucibello, Enrico Malatesta, Marc Mézard, Tamer Mour, Gabriele Perugini, Alon Rosen, Luca Saglietti, Nikolaj I. Schwartzbach, Sofia Vallecorsa, and Riccardo Zecchina.