Ai-Sampler: Adversarial Learning of Markov kernels with involutive maps

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Egorov, Evgenii, Valperga, Ricardo, Gavves, Efstratios
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914823631011840
author Egorov, Evgenii
Valperga, Ricardo
Gavves, Efstratios
author_facet Egorov, Evgenii
Valperga, Ricardo
Gavves, Efstratios
contents Markov chain Monte Carlo methods have become popular in statistics as versatile techniques to sample from complicated probability distributions. In this work, we propose a method to parameterize and train transition kernels of Markov chains to achieve efficient sampling and good mixing. This training procedure minimizes the total variation distance between the stationary distribution of the chain and the empirical distribution of the data. Our approach leverages involutive Metropolis-Hastings kernels constructed from reversible neural networks that ensure detailed balance by construction. We find that reversibility also implies $C_2$-equivariance of the discriminator function which can be used to restrict its function space.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02490
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Ai-Sampler: Adversarial Learning of Markov kernels with involutive maps
Egorov, Evgenii
Valperga, Ricardo
Gavves, Efstratios
Machine Learning
Markov chain Monte Carlo methods have become popular in statistics as versatile techniques to sample from complicated probability distributions. In this work, we propose a method to parameterize and train transition kernels of Markov chains to achieve efficient sampling and good mixing. This training procedure minimizes the total variation distance between the stationary distribution of the chain and the empirical distribution of the data. Our approach leverages involutive Metropolis-Hastings kernels constructed from reversible neural networks that ensure detailed balance by construction. We find that reversibility also implies $C_2$-equivariance of the discriminator function which can be used to restrict its function space.
title Ai-Sampler: Adversarial Learning of Markov kernels with involutive maps
topic Machine Learning
url https://arxiv.org/abs/2406.02490