2 papers
stat.ML2026
The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
Flavio Nicoletti, Chenxiao Ma, Enrico Ventura +2
Real-world datasets are inherently heterogeneous, yet how per-class structural differences and sampling imbalance shape the training dynamics of diffusion models-and potentially ex…
cond-mat.dis-nn2024
Analytical solution to Heisenberg spin glass models on sparse random graphs and their de Almeida-Thouless line
Luca Maria Del Bono, Flavio Nicoletti, Federico Ricci-Tersenghi
Results regarding spin glass models are, to this day, mainly confined to models with Ising spins. Spin glass models with continuous spins exhibit interesting new physical behaviors…