Learning a Restricted Boltzmann Machine using biased Monte Carlo sampling. (arXiv:2206.01310v1 [cs.LG])

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

arxiv boltzmann learning machine sampling