Mixing rates for the Gibbs sampler over Restricted Boltzmann Machines

Abstract: The mixing rate of a Markov chain (Xt)t=0 is the minimum number of steps before the distribution of Xt is close to its stationary distribution with respect to total variation distance. In this talk, we give upper and lower bounds for the mixing rate of a particular Markov chain, the Gibbs sampler over Restricted Boltzmann Machines.