Robust and parallel Bayesian model selection

DOI10.1016/J.CSDA.2018.05.016MaRDI QIDQ1663127zbMATH OpenOpenAlexWikidataFDO

Authors Michael Minyi Zhang, Henry Lam, Lizhen Lin

Publication date 21 August 2018

Published in Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1610.06194

zbMATH Keywords

model selectionmachine learningBayesian statisticsscalable inference

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15) Statistical aspects of big data and data science (62R07)

Abstract: Effective and accurate model selection is an important problem in modern data analysis. One of the major challenges is the computational burden required to handle large data sets that cannot be stored or processed on one machine. Another challenge one may encounter is the presence of outliers and contaminations that damage the inference quality. The parallel "divide and conquer" model selection strategy divides the observations of the full data set into roughly equal subsets and perform inference and model selection independently on each subset. After local subset inference, this method aggregates the posterior model probabilities or other model/variable selection criteria to obtain a final model by using the notion of geometric median. This approach leads to improved concentration in finding the "correct" model and model parameters and also is provably robust to outliers and data contamination.

Recommendations

• Robust and scalable Bayes via a median of subset posterior measures
• Parallel inference for big data with the group Bayesian method
• A general method for robust Bayesian modeling
• Fast robust model selection in large datasets
• Double-parallel Monte Carlo for Bayesian analysis of big data

Cites work

• scientific article; zbMATH DE number 3027356 (Why is no real title available?)
• A new look at the statistical model identification
• Approximation dans les espaces m�triques et th�orie de l'estimation
• Bayesian model averaging: A tutorial. (with comments and a rejoinder).
• Convergence rates of posterior distributions.
• Estimating the dimension of a model
• Geometric median and robust estimation in Banach spaces
• Hilbert space embeddings and metrics on probability measures
• Least angle regression. (With discussion)
• On the empirical estimation of integral probability metrics
• Optimal predictive model selection.
• Spike and slab variable selection: frequentist and Bayesian strategies

Cited in

(6)

• Bayesian predictive model comparison via parallel sampling
• Group projected subspace pursuit for identification of variable coefficient differential equations (GP-IDENT)
• Model-robust subdata selection for big data
• Robust Identification of Differential Equations by Numerical Techniques from a Single Set of Noisy Observation
• Robust and scalable Bayes via a median of subset posterior measures
• Distributed computation for marginal likelihood based model choice

This page was built for publication: Robust and parallel Bayesian model selection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1663127)