A-NICE-MC: Adversarial Training for MCMC

Abstract

Existing Markov Chain Monte Carlo (MCMC) methods are either based on general-purpose and domain-agnostic schemes which can lead to slow convergence, or hand-crafting of problem-specific proposals by an expert. We propose A-NICE-MC, a novel method to train flexible parametric Markov chain kernels to produce samples with desired properties. First, we propose an efficient likelihood-free adversarial training method to train a Markov chain and mimic a given data distribution. Then, we leverage flexible volume preserving flows to obtain parametric kernels for MCMC. Using a bootstrap approach, we show how to train efficient Markov chains to sample from a prescribed posterior distribution by iteratively improving the quality of both the model and the samples. A-NICE-MC provides the first framework to automatically design efficient domain-specific MCMC proposals. Empirical results demonstrate that A-NICE-MC combines the strong guarantees of MCMC with the expressiveness of deep neural networks, and is able to significantly outperform competing methods such as Hamiltonian Monte Carlo.

NIPS 2017

References in corpus (7)

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Improved Training of Wasserstein GANs
• NICE: Non-linear Independent Components Estimation
• Generative Moment Matching Networks
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Learning in Implicit Generative Models
• Measuring Sample Quality with Kernels

Cited by in corpus (33)

• Denoising Diffusion Probabilistic Models
• Generative Modeling by Estimating Gradients of the Data Distribution
• Normalizing Flows for Probabilistic Modeling and Inference
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Event Generation with Normalizing Flows
• Neural Network Renormalization Group
• i-flow: High-dimensional Integration and Sampling with Normalizing Flows
• Denoising Diffusion Implicit Models
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• Unbiased Monte Carlo Cluster Updates with Autoregressive Neural Networks
• Accelerated Bayesian inference using deep learning
• Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint
• Likelihood-free MCMC with Amortized Approximate Ratio Estimators
• Neural Canonical Transformation with Symplectic Flows
• Generalizing Hamiltonian Monte Carlo with Neural Networks
• Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
• Metropolis-Hastings Generative Adversarial Networks
• Stochastic Normalizing Flows
• Stein Neural Sampler
• Exponential Family Estimation via Adversarial Dynamics Embedding
• Normalizing flows as an enhanced sampling method for atomistic supercooled liquids
• MintNet: Building Invertible Neural Networks with Masked Convolutions
• Higher Order Hamiltonian Monte Carlo Sampling for Cosmological Large-Scale Structure Analysis
• Metropolis-Hastings view on variational inference and adversarial training
• Kernel Implicit Variational Inference
• Path Integral Sampler: a stochastic control approach for sampling
• Adaptive Monte Carlo augmented with normalizing flows
• Ergodic Inference: Accelerate Convergence by Optimisation
• A Neural Network MCMC sampler that maximizes Proposal Entropy
• Learning Non-linear Wavelet Transformation via Normalizing Flow
• Quantification of Predictive Uncertainty via Inference-Time Sampling
• Towards Arbitrary Noise Augmentation - Deep Learning for Sampling from Arbitrary Probability Distributions
• LSB: Local Self-Balancing MCMC in Discrete Spaces