A General Framework for Updating Belief Distributions

DOI10.1111/RSSB.12158zbMATH Open1414.62039arXiv1306.6430OpenAlexW3099663651WikidataQ37371195 ScholiaQ37371195MaRDI QIDQ5378383FDOQ5378383

Authors: Pier Giovanni Bissiri, Chris Holmes, Stephen G. Walker 

Publication date: 12 June 2019

Published in: Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)

Abstract: We propose a framework for general Bayesian inference. We argue that a valid update of a prior belief distribution to a posterior can be made for parameters which are connected to observations through a loss function rather than the traditional likelihood function, which is recovered under the special case of using self information loss. Modern application areas make it is increasingly challenging for Bayesians to attempt to model the true data generating mechanism. Moreover, when the object of interest is low dimensional, such as a mean or median, it is cumbersome to have to achieve this via a complete model for the whole data distribution. More importantly, there are settings where the parameter of interest does not directly index a family of density functions and thus the Bayesian approach to learning about such parameters is currently regarded as problematic. Our proposed framework uses loss-functions to connect information in the data to functionals of interest. The updating of beliefs then follows from a decision theoretic approach involving cumulative loss functions. Importantly, the procedure coincides with Bayesian updating when a true likelihood is known, yet provides coherent subjective inference in much more general settings. Connections to other inference frameworks are highlighted.

Full work available at URL: https://arxiv.org/abs/1306.6430

Recommendations

• scientific article; zbMATH DE number 1759389
• Update of Probabilistic Beliefs: Implementation and Parametric Verification
• Publication:3795274
• Bayesian updating and belief functions
• scientific article; zbMATH DE number 1882053
• scientific article
• A Unified View of Belief Revision and Update
• Bayesian updating rules and AGM belief revision
• Dynamically consistent updating of multiple prior beliefs -- an algorithmic approach
• scientific article; zbMATH DE number 3868426

zbMATH Keywords

informationdecision theorygeneralized estimating equationsmaximum entropyloss functionself-information loss functiongeneral Bayesian updatingGibbs posteriorsprovably approximately correct Bayes methods

Mathematics Subject Classification ID

Bayesian inference (62F15) Bayesian problems; characterization of Bayes procedures (62C10)

Cited In (92)

• Generalized Bayes approach to inverse problems with model misspecification
• Bayesian fractional posteriors
• Title not available (Why is that?)
• A modern retrospective on probabilistic numerics
• Title not available (Why is that?)
• Robust Bayes-like estimation: rho-Bayes estimation
• On Bayesian oracle properties
• Title not available (Why is that?)
• Bayes posterior convergence for loss functions via almost additive thermodynamic formalism
• Transport Monte Carlo: High-Accuracy Posterior Approximation via Random Transport
• General Bayesian updating and the loss-likelihood bootstrap
• Approximate models and robust decisions
• Learning attribute patterns in high-dimensional structured latent attribute models
• Title not available (Why is that?)
• A discrete density approach to Bayesian quantile and expectile regression with discrete responses
• Bayesian updating rules and AGM belief revision
• Gibbs posterior inference on value-at-risk
• Communication-efficient distributed statistical inference
• Leave Pima Indians alone: binary regression as a benchmark for Bayesian computation
• Title not available (Why is that?)
• Fast Calibrated Additive Quantile Regression
• AQUA: automated quantized inference for probabilistic programs
• Variable selection in panel models with breaks
• Multilevel Monte Carlo acceleration of seismic wave propagation under uncertainty
• An efficient adaptive MCMC algorithm for pseudo-Bayesian quantum tomography
• A generalized likelihood-based Bayesian approach for scalable joint regression and covariance selection in high dimensions
• Random weighting in LASSO regression
• Gibbs posterior inference on the minimum clinically important difference
• Joint production in stochastic non-parametric envelopment of data with firm-specific directions
• Nonparametric Bayesian clay for robust decision bricks
• Rejoinder: Approximate models and robust decisions
• Update of Probabilistic Beliefs: Implementation and Parametric Verification
• Robust approximate Bayesian inference
• Robust estimation in controlled branching processes: Bayesian estimators via disparities
• An oracle inequality for quasi-Bayesian nonnegative matrix factorization
• Bayesian Probabilistic Numerical Methods
• Bayesian functional registration of fMRI activation maps
• Fast rates for general unbounded loss functions: from ERM to generalized Bayes
• Detecting conflicting summary statistics in likelihood-free inference
• Gibbs posterior inference on multivariate quantiles
• Robust Approximate Bayesian Inference With Synthetic Likelihood
• Model-free posterior inference on the area under the receiver operating characteristic curve
• Robust and rate-optimal Gibbs posterior inference on the boundary of a noisy image
• On general Bayesian inference using loss functions
• Estimating promotion effects in email marketing using a large-scale cross-classified Bayesian joint model for nested imbalanced data
• `Purposely misspecified' posterior inference on the volatility of a jump diffusion process
• Inference and computation with generalized additive models and their extensions
• Gibbs posterior concentration rates under sub-exponential type losses
• Pseudo-Bayesian quantum tomography with rank-adaptation
• Bayesian Inference Using Synthetic Likelihood: Asymptotics and Adjustments
• Title not available (Why is that?)
• Observational nonidentifiability, generalized likelihood and free energy
• Gibbs posterior convergence and the thermodynamic formalism
• Model misspecification, Bayesian versus credibility estimation, and Gibbs posteriors
• Bayesian inference via projections
• \(\alpha\)-variational inference with statistical guarantees
• Variational Bayes in State Space Models: Inferential and Predictive Accuracy
• Robust heavy-tailed versions of generalized linear models with applications in actuarial science
• From robust tests to Bayes-like posterior distributions
• A diffusion-based spatio-temporal extension of Gaussian Matérn fields
• Decisions, decisions, decisions in an uncertain environment
• Bayesian inference using least median of squares and least trimmed squares in models with independent or correlated errors and outliers
• Non-parametric local capability indices for industrial planar manufacts: an application to the etching phase in the microelectronic industry
• An enriched mixture model for functional clustering
• Approximate Bayesian computation via classification
• Modularized Bayesian analyses and cutting feedback in likelihood-free inference
• Posterior consistency for the spectral density of non‐Gaussian stationary time series
• Title not available (Why is that?)
• Generalized Bayes Quantification Learning under Dataset Shift
• Variational inference for cutting feedback in misspecified models
• Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
• Probabilistic contrastive dimension reduction for case-control study data
• Generalised likelihood profiles for models with intractable likelihoods
• A nonparametric Bayesian method for dose finding in drug combinations cancer trials
• Bayesian variable selection with a pleiotropic loss function in Mendelian randomization
• Adaptive variable selection for sequential prediction in multivariate dynamic models
• Forecasting the risk of cryptocurrencies: comparison and combination of GARCH and stochastic volatility models
• Generalized Bayesian Inference for Discrete Intractable Likelihood
• Generalized Bayesian likelihood-free inference
• Bayesian decision-theoretic design of experiments under an alternative model
• A reduced-rank approach to predicting multiple binary responses through machine learning
• A comparison of learning rate selection methods in generalized Bayesian inference
• Adaptation of the tuning parameter in general Bayesian inference with robust divergence
• Quantification of empirical determinacy: The impact of likelihood weighting on posterior location and spread in Bayesian meta-analysis estimated with JAGS and INLA
• Minimax Quasi-Bayesian Estimation in Sparse Canonical Correlation Analysis via a Rayleigh Quotient Function
• Robust posterior inference for Youden’s index cutoff
• High-dimensional sparse classification using exponential weighting with empirical hinge loss
• Approximating Bayes in the 21st century
• Sampling algorithms in statistical physics: a guide for statistics and machine learning
• Bernstein-von Mises theorem and misspecified models: a review
• Causal inference under mis-specification: adjustment based on the propensity score (with discussion)
• User-friendly Introduction to PAC-Bayes Bounds

This page was built for publication: A General Framework for Updating Belief Distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5378383)