activity
20162020
most citedA fast and accurate algorithm for inferring sparse Ising models via parameters activation to maximize the pseudo-likelihood

5 citations · 5 across the 1 of their papers we have counts for

collaborators
Showing cond-mat.dis-nnShow all

7 papers · 1 filter

cond-mat.dis-nn2020

On the number of limit cycles in diluted neural networks

Sungmin Hwang, Enrico Lanza, Giorgio Parisi +3

We consider the storage properties of temporal patterns, i.e. cycles of finite lengths, in neural networks represented by (generally asymmetric) spin glasses defined on random grap…

cond-mat.dis-nn2019

Large deviations of glassy effective potentials

Silvio Franz, Jacopo Rocchi

The theory of glassy fluctuations can be formulated in terms of disordered effective potentials. While the properties of the average potentials are well understood, the study of th…

cond-mat.dis-nn2019

Inverse problems for structured datasets using parallel TAP equations and RBM

Aurélien Decelle, Sungmin Hwang, Jacopo Rocchi +1

We propose an efficient algorithm to solve inverse problems in the presence of binary clustered datasets. We consider the paradigmatic Hopfield model in a teacher student scenario,…

cond-mat.dis-nn2019★ 5 cited

A fast and accurate algorithm for inferring sparse Ising models via parameters activation to maximize the pseudo-likelihood

Silvio Franz, Federico Ricci-Tersenghi, Jacopo Rocchi

We propose a new algorithm to learn the network of the interactions of pairwise Ising models. The algorithm is based on the pseudo-likelihood method (PLM), that has already been pr…

cond-mat.dis-nn2017

Slow Spin Dynamics and Self-Sustained Clusters in Sparsely Connected Systems

Jacopo Rocchi, David Saad, Chi Ho Yeung

To identify emerging microscopic structures in low temperature spin glasses, we study self-sustained clusters (SSC) in spin models defined on sparse random graphs. A message-passin…

cond-mat.dis-nn2017

High storage capacity in the Hopfield model with auto-interactions - stability analysis

Jacopo Rocchi, David Saad, Daniele Tantari

Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfield associative memory model, well beyond the limits obtained previously. We inve…