148 citations · 199 across the 4 of their papers we have counts for
6 papers
First Learn, Then Memorize: The Spectral Bias of Diffusion Models
Raphaël Urfin, Tony Bonnaire, Giulio Biroli +1
Diffusion models trained on a finite dataset first learn to generate novel, high-quality samples and only much later collapse onto their training set. We identify the mechanism beh…
Double Descent and Malign Overfitting in Diffusion Models
Raphaël Urfin, Tony Bonnaire, Giulio Biroli +1
Conventional wisdom in deep learning holds that overparameterization---having more parameters than training samples ---is benign: larger models generalize better and, even w…
Kernel Density Estimators in Large Dimensions
Giulio Biroli, Marc Mézard
This paper studies Kernel Density Estimation for a high-dimensional distribution . Traditional approaches have focused on the limit of large number of data points and fix…
Dynamical Regimes of Diffusion Models
Giulio Biroli, Tony Bonnaire, Valentin de Bortoli +1
Using statistical physics methods, we study generative diffusion models in the regime where the dimension of space and the number of data are large, and the score function has been…
Eigenvector Dreaming
Marco Benedetti, Louis Carillo, Enzo Marinari +1
Among the performance-enhancing procedures for Hopfield-type networks that implement associative memory, Hebbian Unlearning (or dreaming) strikes for its simplicity and its clear b…
Glass models on Bethe lattices
O. Rivoire, G. Biroli, O. C. Martin +1
We consider ``lattice glass models'' in which each site can be occupied by at most one particle, and any particle may have at most l occupied nearest neighbors. Using the cavity me…