Minimax formula for the replica symmetric free energy of deep restricted Boltzmann machines

Abstract

We study the free energy of a most used deep architecture for restricted Boltzmann machines, where the layers are disposed in series. Assuming independent Gaussian distributed random weights, we show that the error term in the so-called replica symmetric sum rule can be optimised as a saddle point. This leads us to conjecture that in the replica symmetric approximation the free energy is given by a $minmax$ formula, which parallels the one achieved for two-layer case.