35 citations · 106 across the 15 of their papers we have counts for
15 papers
Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
Jean Barbier, Francesco Camilli, Minh-Toan Nguyen +2
For four decades statistical physics has been providing a framework to analyse neural networks. A long-standing question remained on its capacity to tackle deep learning models cap…
Statistical mechanics of extensive-width Bayesian neural networks near interpolation
Jean Barbier, Francesco Camilli, Minh-Toan Nguyen +2
For three decades statistical mechanics has been providing a framework to analyse neural networks. However, the theoretically tractable models, e.g., perceptrons, random features m…
Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation
Jean Barbier, Francesco Camilli, Minh-Toan Nguyen +2
We consider a teacher-student model of supervised learning with a fully-trained two-layer neural network whose width and input dimension are large and proportional. We prov…
Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers
Federico Bassetti, Marco Gherardi, Alessandro Ingrosso +2
Deep linear networks have been extensively studied, as they provide simplified models of deep learning. However, little is known in the case of finite-width architectures with mult…
Restoring balance: principled under/oversampling of data for optimal classification
Emanuele Loffredo, Mauro Pastore, Simona Cocco +1
Class imbalance in real-world data poses a common bottleneck for machine learning tasks, since achieving good generalization on under-represented examples is often challenging. Mit…
Random features and polynomial rules
Fabián Aguirre-López, Silvio Franz, Mauro Pastore
Random features models play a distinguished role in the theory of deep learning, describing the behavior of neural networks close to their infinite-width limit. In this work, we pr…
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit
R. Pacelli, S. Ariosto, M. Pastore +3
Despite the practical success of deep neural networks, a comprehensive theoretical framework that can predict practically relevant scores, such as the test accuracy, from knowledge…
Satisfiability transition in asymmetric neural networks
Fabián Aguirre-López, Mauro Pastore, Silvio Franz
Asymmetry in the synaptic interactions between neurons plays a crucial role in determining the memory storage and retrieval properties of recurrent neural networks. In this work, w…
Critical properties of the SAT/UNSAT transitions in the classification problem of structured data
Mauro Pastore
The classification problem of structured data can be solved with different strategies: a supervised learning approach, starting from a labeled training set, and an unsupervised lea…
Self-induced glassy phase in multimodal cavity quantum electrodynamics
Vittorio Erba, Mauro Pastore, Pietro Rotondo
We provide strong evidence that the effective spin-spin interaction in a multimodal confocal optical cavity gives rise to a self-induced glassy phase, which emerges exclusively fro…
Statistical learning theory of structured data
Mauro Pastore, Pietro Rotondo, Vittorio Erba +1
The traditional approach of statistical physics to supervised learning routinely assumes unrealistic generative models for the data: usually inputs are independent random variables…
Beyond the storage capacity: data driven satisfiability transition
Pietro Rotondo, Mauro Pastore, Marco Gherardi
Data structure has a dramatic impact on the properties of neural networks, yet its significance in the established theoretical frameworks is poorly understood. Here we compute the…
Large deviations of the free energy in the p-spin glass spherical model
Mauro Pastore, Andrea Di Gioacchino, Pietro Rotondo
We investigate the behavior of the rare fluctuations of the free energy in the p-spin spherical model, evaluating the corresponding rate function via the Gärtner-Ellis theorem. Thi…
Lattice QCD effective action with Bogoliubov transformations
Sergio Caracciolo, Mauro Pastore
In the Wilson's lattice formulation of QCD, a fermionic Fock space of states can be explicitly built at each time slice using canonical creation and annihilation operators. The par…
Effective mesonic theory for the 't Hooft model on the lattice
Sergio Caracciolo, Mauro Pastore
We apply to a lattice version of the 't~Hooft model, QCD in two space-time dimensions for large number of colours, a method recently proposed to obtain an effective mesonic action…