Nonreversible MCMC from conditional invertible transforms: a complete recipe with convergence guarantees
arXiv:2012.15550
Abstract
Markov Chain Monte Carlo (MCMC) is a class of algorithms to sample complex and high-dimensional probability distributions. The Metropolis-Hastings (MH) algorithm, the workhorse of MCMC, provides a simple recipe to construct reversible Markov kernels. Reversibility is a tractable property that implies a less tractable but essential property here, invariance. Reversibility is however not necessarily desirable when considering performance. This has prompted recent interest in designing kernels breaking this property. At the same time, an active stream of research has focused on the design of novel versions of the MH kernel, some nonreversible, relying on the use of complex invertible deterministic transforms. While standard implementations of the MH kernel are well understood, the aforementioned developments have not received the same systematic treatment to ensure their validity. This paper fills the gap by developing general tools to ensure that a class of nonreversible Markov kernels, possibly relying on complex transforms, has the desired invariance property and leads to convergent algorithms. This leads to a set of simple and practically verifiable conditions.
References in corpus (10)
- Density estimation using Real NVP
- Normalizing Flows for Probabilistic Modeling and Inference
- Guided Image Generation with Conditional Invertible Neural Networks
- Flow-based generative models for Markov chain Monte Carlo in lattice field theory
- Irreversible Monte Carlo Algorithms for Efficient Sampling
- Compressible Generalized Hybrid Monte Carlo
- On the convergence of Hamiltonian Monte Carlo
- Hamiltonian Monte Carlo Without Detailed Balance
- Deep Involutive Generative Models for Neural MCMC
- MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference