collaborators

6 papers

cs.LG2026

Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks

Francesco D'Amico, Dario Bocchi, Matteo Negri

Scaling laws in deep learning -- empirical power-law relationships linking model performance to resource growth -- have emerged as simple yet striking regularities across architect…

cs.LG2026

Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data

Bao Pham, Mohammed J. Zaki, Luca Ambrogioni +2

When do language diffusion models memorize their training data, and how to quantitatively assess their true generative regime? We address these questions by showing that Uniform-ba…

cs.LG2026

Memorization to Generalization: Emergence of Diffusion Models from Associative Memory

Bao Pham, Gabriel Raya, Matteo Negri +3

Dense Associative Memories (DenseAMs) are generalizations of Hopfield networks, which have superior information storage capacity and can store training data points (memories) at lo…

cond-mat.dis-nn2026

Benchmarking Graph Neural Networks in Solving Hard Constraint Satisfaction Problems

Geri Skenderi, Lorenzo Buffoni, Francesco D'Amico +6

Graph neural networks (GNNs) are increasingly applied to hard optimization problems, often claiming superiority over classical heuristics. However, such claims risk being unsolid d…

cond-mat.dis-nn2025

Statistical mechanics of vector Hopfield network near and above saturation

Flavio Nicoletti, Francesco D'Amico, Matteo Negri

We study analytically and numerically a Hopfield fully-connected network with -dimensional vector spins. These networks are models of associative memory that generalize the stan…

cond-mat.stat-mech2025

Pseudo-likelihood produces associative memories able to generalize, even for asymmetric couplings

Francesco D'Amico, Dario Bocchi, Luca Maria Del Bono +2

Energy-based probabilistic models learned by maximizing the likelihood of the data are limited by the intractability of the partition function. A widely used workaround is to maxim…