32 citations · 49 across the 7 of their papers we have counts for
12 papers
Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models
Thomas Tulinski, Simona Cocco, Rémi Monasson +1
Energy-based models (EBMs) are flexible generative architectures inspired by statistical physics, but their learning and generative properties remain poorly understood. Here, we an…
Replica Theory of Spherical Boltzmann Machine Ensembles
Thomas Tulinski, Jorge Fernandez-De-Cossio-Diaz, Simona Cocco +1
Training in machine learning generally consists in finding one model, whose parameters minimize a data-dependent loss. Yet, empirical work shows that ensemble learning, an approach…
A High-Order Cumulant Extension of Quasi-Linkage Equilibrium
Kai S. Shimagaki, Jorge Fernandez-de-Cossio-Diaz, Mauro Pastore +3
A central question in evolutionary biology is how to quantitatively understand the dynamics of genetically diverse populations. Modeling the genotype distribution is challenging, a…
Disentangling representations in Restricted Boltzmann Machines without adversaries
Jorge Fernandez-de-Cossio-Diaz, Simona Cocco, Remi Monasson
A goal of unsupervised machine learning is to build representations of complex high-dimensional data, with simple relations to their properties. Such disentangled representations m…
Inferring metabolic fluxes in nutrient-limited continuous cultures: A Maximum Entropy Approach with minimum information
Jose A. Pereiro-Morejón, Jorge Fernández-de-Cossio-Díaz, R. Mulet
We propose a new scheme to infer the metabolic fluxes of cell cultures in a chemostat. Our approach is based on the Maximum Entropy Principle and exploits the understanding of the…
Spin Glass Theory of Interacting Metabolic Networks
Jorge Fernandez-de-Cossio-Diaz, Roberto Mulet
We cast the metabolism of interacting cells within a statistical mechanics framework considering both, the actual phenotypic capacities of each cell and its interaction with its ne…