Modelling conditional probabilities with Riemann-Theta Boltzmann Machines
This is an incremental theoretical contribution for researchers working with Boltzmann machines and probabilistic modeling.
The paper tackled the problem of modeling conditional probabilities in Riemann-Theta Boltzmann Machines by deriving that the conditional density function is a reparameterization of the original model, enabling direct inference without additional computations.
The probability density function for the visible sector of a Riemann-Theta Boltzmann machine can be taken conditional on a subset of the visible units. We derive that the corresponding conditional density function is given by a reparameterization of the Riemann-Theta Boltzmann machine modelling the original probability density function. Therefore the conditional densities can be directly inferred from the Riemann-Theta Boltzmann machine.