Metropolis-Hastings view on variational inference and adversarial training

Abstract

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. On real-world datasets, we improve Frechet Inception Distance and Inception Score, using different GANs as a proposal distribution for the MH algorithm. In particular, we demonstrate improvements of recently proposed BigGAN model on ImageNet.

References in corpus (13)

• Auto-Encoding Variational Bayes
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• NICE: Non-linear Independent Components Estimation
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Density estimation using Real NVP
• Adversarial Feature Learning
• A Note on the Inception Score
• Austerity in MCMC Land: Cutting the Metropolis-Hastings Budget
• A Review of Multiple Try MCMC algorithms for Signal Processing
• A-NICE-MC: Adversarial Training for MCMC
• Generalizing Hamiltonian Monte Carlo with Neural Networks

Cited by in corpus (6)

• Metropolis-Hastings Generative Adversarial Networks
• A Neural Network MCMC sampler that maximizes Proposal Entropy
• Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functions
• Decentralized Langevin Dynamics over a Directed Graph
• A Metropolized adaptive subspace algorithm for high-dimensional Bayesian variable selection
• The Implicit Metropolis-Hastings Algorithm