A transportation approach to the mean-field approximation

We develop transportation-entropy inequalities which are saturated for measures such that their log-density with respect to the background measure is an affine function, in the setting of the uniform measure on the discrete hypercube and the exponential measure. In this sense, this extends the well-known result of Talagrand in the Gaussian case. By duality, these transportation-entropy inequalities imply a strong integrability inequality for Bernoulli and exponential processes. As a result, we obtain a dimension-free mean-field approximation of the free energy of a Gibbs measure and a dimension-free nonlinear large deviations bound on the discrete hypercube. Applied to the Ising model, we deduce that the mean-field approximation is within $O(\sqrt{n}\mathrm{\mid }\mathrm{\mid }J\mathrm{\mid }{\mathrm{\mid }}_2)$ of the free energy, where $n$ is the number of spins and $\mathrm{\mid }\mathrm{\mid }J\mathrm{\mid }{\mathrm{\mid }}_2$ is the Hilbert-Schmidt norm of the interaction matrix. Finally, we obtain a reverse log-Sobolev inequality on the discrete hypercube similar to the one proved recently in the Gaussian case by Eldan and Ledoux.