Learning a Restricted Boltzmann Machine using biased Monte Carlo sampling. (arXiv:2206.01310v2 [cs.LG] UPDATED)

Restricted Boltzmann Machines are simple and powerful generative models that
can encode any complex dataset. Despite all their advantages, in practice the
trainings are often unstable and it is difficult to assess their quality
because the dynamics are affected by extremely slow time dependencies. This
situation becomes critical when dealing with low-dimensional clustered
datasets, where the time required to sample ergodically the trained models
becomes computationally prohibitive. In this work, we show that this divergence
of Monte Carlo mixing times …

arxiv boltzmann machine sampling