Approximate Inference with Amortised MCMC

Abstract

We propose a novel approximate inference algorithm that approximates a target distribution by amortising the dynamics of a user-selected MCMC sampler. The idea is to initialise MCMC using samples from an approximation network, apply the MCMC operator to improve these samples, and finally use the samples to update the approximation network thereby improving its quality. This provides a new generic framework for approximate inference, allowing us to deploy highly complex, or implicitly defined approximation families with intractable densities, including approximations produced by warping a source of randomness through a deep neural network. Experiments consider image modelling with deep generative models as a challenging test for the method. Deep models trained using amortised MCMC are shown to generate realistic looking samples as well as producing diverse imputations for images with regions of missing pixels.

References in corpus (7)

• Expectation Propagation for approximate Bayesian inference
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Learning in Implicit Generative Models
• Variational Bayesian Inference with Stochastic Search
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
• Variational Inference using Implicit Distributions

Cited by in corpus (18)

• Gradient Estimators for Implicit Models
• ZhuSuan: A Library for Bayesian Deep Learning
• Adversarial Distillation of Bayesian Neural Network Posteriors
• Learning to Draw Samples with Amortized Stein Variational Gradient Descent
• Advances in Variational Inference
• Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
• Markovian Score Climbing: Variational Inference with KL(p||q)
• Variational Implicit Processes
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
• Learning Proposals for Probabilistic Programs with Inference Combinators
• Kernel Implicit Variational Inference
• Ergodic Inference: Accelerate Convergence by Optimisation
• Implicit Deep Latent Variable Models for Text Generation
• Amortized Population Gibbs Samplers with Neural Sufficient Statistics
• All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
• MCMC Variational Inference via Uncorrected Hamiltonian Annealing
• Reparameterized Sampling for Generative Adversarial Networks
• MCMC-Interactive Variational Inference