Approximate Inference with Amortised MCMC

2017/02/27 by Yingzhen Li, Richard E. Turner, Li, Yingzhen +3 · 1 citation
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.1702.08343

openalex publication_date 2017/02/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Playing Atari with Deep Reinforcement Learning
• Auto-Encoding Variational Bayes
• Training Products of Experts by Minimizing Contrastive Divergence
• Rényi Divergence Variational Inference
• Stein Variational Gradient Descent: A General Purpose Bayesian Inference\n Algorithm
• Learning in Implicit Generative Models
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Cited by

• Adversarial Distillation of Bayesian Neural Network Posteriors

Related

• Neural Methods for Amortized Inference
• Amortized Bayesian Workflow
• Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
• Scalable Approximate Inference and Some Applications
• Learning Deep Generative Models with Doubly Stochastic MCMC