Metropolis-Hastings view on variational inference and adversarial training

Understand

A significant part of MCMC methods can be considered as the Metropolis-Hastings (MH) algorithm with different proposal distributions.

• From this point of view, the problem of constructing a sampler can be reduced to the question - how to choose a proposal for the MH algorithm? To address this question, we propose to learn an independent sampler that maximizes the acceptance rate of the MH algorithm, which, as we demonstrate, is highly related to the conventional variational inference.
• For Bayesian inference, the proposed method compares favorably against alternatives to sample from the posterior distribution.
• Under the same approach, we step beyond the scope of classical MCMC methods and deduce the Generative Adversarial Networks (GANs) framework from scratch, treating the generator as the proposal and the discriminator as the acceptance test.