Mean-field variational approximate Bayesian inference for latent variable models

被引：39

作者：

Consonni, Guido ^{[2
]}

Marin, Jean-Michel ^{[1
]}

机构：

[1] Univ Orsay, Lab Math Bat 425, INRIA FUTURS Projects SELECT, F-91405 Orsay, France

[2] Univ Pavia, Dept Econ & Quantitat Methods, I-27100 Pavia, Italy

来源：

COMPUTATIONAL STATISTICS & DATA ANALYSIS | 2007年 / 52卷 / 02期

关键词：

bayesian inference; Bayesian probit model; Gibbs sampling; latent variable models; marginal distribution; mean-field variational methods;

D O I：

10.1016/j.csda.2006.10.028

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

The ill-posed nature of missing variable models offers a challenging testing ground for new computational techniques. This is the case for the mean-field variational Bayesian inference. The behavior of this approach in the setting of the Bayesian probit model is illustrated. It is shown that the mean-field variational method always underestimates the posterior variance and, that, for small sample sizes, the mean-field variational approximation to the posterior location could be poor. (c) 2006 Elsevier B.V. All rights reserved.

引用

页码：790 / 798

页数：9

共 50 条

[21] A Fixed-Point Operator for Inference in Variational Bayesian Latent Gaussian Models
Sheth, Rishit
Khardon, Roni
ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 51, 2016, 51 : 761 - 769
[22] Mean-Field Approximate Optimization Algorithm
Misra-Spieldenner, Aditi
Bode, Tim
Schuhmacher, Peter K.
Stollenwerk, Tobias
Bagrets, Dmitry
Wilhelm, Frank K.
PRX QUANTUM, 2023, 4 (03):
[23] Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models
Gal, Yarin
van der Wilk, Mark
Rasmussen, Carl E.
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 2014, 27
[24] Generalised Gaussian Process Latent Variable Models (GPLVM) with Stochastic Variational Inference
Lalchand, Vidhi
Ravuri, Aditya
Lawrence, Neil D.
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
[25] Approximate Bayesian Inference for Survival Models
Martino, Sara
Akerkar, Rupali
Rue, Havard
SCANDINAVIAN JOURNAL OF STATISTICS, 2011, 38 (03) : 514 - 528
[26] Variational mean-field algorithm for efficient inference in large systems of stochastic differential equations
Vrettas, Michail D.
Opper, Manfred
Cornford, Dan
PHYSICAL REVIEW E, 2015, 91 (01):
[27] Approximate Bayesian inference for hierarchical Gaussian Markov random field models
Rue, Havard
Martino, Sara
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2007, 137 (10) : 3177 - 3192
[28] Pseudo-marginal Bayesian inference for Gaussian process latent variable models
C. Gadd
S. Wade
A. A. Shah
Machine Learning, 2021, 110 : 1105 - 1143
[29] Pseudo-marginal Bayesian inference for Gaussian process latent variable models
Gadd, C.
Wade, S.
Shah, A. A.
MACHINE LEARNING, 2021, 110 (06) : 1105 - 1143
[30] Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations
Rue, Havard
Martino, Sara
Chopin, Nicolas
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2009, 71 : 319 - 392

← 1 2 3 4 5 →