80 citations · 645 across the 38 of their papers we have counts for
6 papers · 1 filter
A dynamic network model with persistent links and node-specific latent variables, with an application to the interbank market
Piero Mazzarisi, Paolo Barucca, Fabrizio Lillo +1
We propose a dynamic network model where two mechanisms control the probability of a link between two nodes: (i) the existence or absence of this link in the past, and (ii) node-sp…
Overlap synchronisation in multipartite random energy models
Giuseppe Genovese, Daniele Tantari
In a multipartite random energy model, made of a number of coupled GREMs, we determine the joint law of the overlaps in terms of the ones of the single GREMs. This provides the sim…
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…
Neural Networks retrieving Boolean patterns in a sea of Gaussian ones
Elena Agliari, Adriano Barra, Chiara Longo +1
Restricted Boltzmann Machines are key tools in Machine Learning and are described by the energy function of bipartite spin-glasses. From a statistical mechanical perspective, they…
Phase Diagram of Restricted Boltzmann Machines and Generalised Hopfield Networks with Arbitrary Priors
Adriano Barra, Giuseppe Genovese, Peter Sollich +1
Restricted Boltzmann Machines are described by the Gibbs measure of a bipartite spin glass, which in turn corresponds to the one of a generalised Hopfield network. This equivalence…
Disentangling group and link persistence in Dynamic Stochastic Block models
Paolo Barucca, Fabrizio Lillo, Piero Mazzarisi +1
We study the inference of a model of dynamic networks in which both communities and links keep memory of previous network states. By considering maximum likelihood inference from s…