Hybrid unadjusted Langevin methods for high-dimensional latent variable models

DOI10.1016/j.jeconom.2024.105741MaRDI QIDQ6554220

Didier Nibbering, Rubén Loaiza-Maya, Dan Zhu

Publication date: 12 June 2024

Published in: Journal of Econometrics (Search for Journal in Brave)

zbMATH Keywords

Markov chain Monte Carlolatent variable modelsunadjusted Langevin algorithm

Mathematics Subject Classification ID

Statistics (62-XX) Game theory, economics, finance, and other social and behavioral sciences (91-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• A Bayesian analysis of the multinomial probit model using marginal data augmentation
• Exponential convergence of Langevin distributions and their discrete approximations
• Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
• Fast and accurate variational inference for models with many latent variables
• Inference in hidden Markov models.
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• (Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics
• Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
• Speeding Up MCMC by Efficient Data Subsampling
• Tests of Conditional Predictive Ability
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Stochastic Gradient Markov Chain Monte Carlo
• Fast Variational Bayes Methods for Multinomial Probit Models
• Scalable Bayesian Estimation in the Multinomial Probit Model
• Gaussian variational approximations for high-dimensional state space models

This page was built for publication: Hybrid unadjusted Langevin methods for high-dimensional latent variable models