Spin glasses, overlap gap and learning

by Victor Issa

Monday Jan 26, 2026, 4:30 PM → 5:30 PM Europe/Paris

S435 (UMPA)

In this talk we will explore the link between problems related to the statistical physics of disordered systems and the procedures used in practice to design and train neural networks in modern machine learning. We will put a special emphasis on the question of uniqueness of Parisi measures for spin glasses and the related overlap gap property which has been recently been put forward as a barrier for efficient optimization.