Markov Chain Monte Carlo

Deep generative classifier uses Short Run Markov Chain Monte Carlo inference, Langevin dynamics, and backpropagation through time to achieve similar classification accuracy as an analogous discriminative classifier, i.e., a convolutional neural network, while it has the advantages that it can generate data, it can learn unsupervised with additional unlabeled data, and it exhibits robustness to adversarial attacks due to the stochasticity of the Langevin equation and the top-down architecture of the underlying generator network.

Short-run MCMC residual network outperforms a variational autoencoder in regard to image reconstruction error and image synthesis quality, while not requiring the design of a separate inference network

Convergence analysis of exact sampling with Gibbs sampler and coupled Markov chains vs. cluster sampling with Swendsen-Wang algorithm