MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference

Abstract

In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC). This approach can be used with generic MCMC kernels, but is especially well suited to \textit{MetFlow}, a novel family of MCMC algorithms we introduce, in which proposals are obtained using Normalizing Flows. The marginal distribution produced by such MCMC algorithms is a mixture of flow-based distributions, thus drastically increasing the expressivity of the variational family. Unlike previous methods following this direction, our approach is amenable to the reparametrization trick and does not rely on computationally expensive reverse kernels. Extensive numerical experiments show clear computational and performance improvements over state-of-the-art methods.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• MCMC using Hamiltonian dynamics
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Normalizing Flows: An Introduction and Review of Current Methods
• Density estimation using Real NVP
• Pyro: Deep Universal Probabilistic Programming
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Geometric integrators and the Hamiltonian Monte Carlo method
• NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
• Generalizing Hamiltonian Monte Carlo with Neural Networks
• Variational Inference with Hamiltonian Monte Carlo
• Quasi Markov Chain Monte Carlo Methods

Cited by in corpus (4)

• A general perspective on the Metropolis-Hastings kernel
• Nonreversible MCMC from conditional invertible transforms: a complete recipe with convergence guarantees
• Accelerating MCMC algorithms through Bayesian Deep Networks
• Measure Transport with Kernel Stein Discrepancy