Likelihood-free inference via classification

DOI10.1007/S11222-017-9738-6zbMATH Open1384.62089arXiv1407.4981OpenAlexW1502641836WikidataQ93048021 ScholiaQ93048021MaRDI QIDQ1702017FDOQ1702017

Samuel Kaski, Michael U. Gutmann, Jukka Corander, Ritabrata Dutta

Publication date: 27 February 2018

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: Increasingly complex generative models are being used across disciplines as they allow for realistic characterization of data, but a common difficulty with them is the prohibitively large computational cost to evaluate the likelihood function and thus to perform likelihood-based statistical inference. A likelihood-free inference framework has emerged where the parameters are identified by finding values that yield simulated data resembling the observed data. While widely applicable, a major difficulty in this framework is how to measure the discrepancy between the simulated and observed data. Transforming the original problem into a problem of classifying the data into simulated versus observed, we find that classification accuracy can be used to assess the discrepancy. The complete arsenal of classification methods becomes thereby available for inference of intractable generative models. We validate our approach using theory and simulations for both point estimation and Bayesian inference, and demonstrate its use on real data by inferring an individual-based epidemiological model for bacterial infections in child care centers.

Full work available at URL: https://arxiv.org/abs/1407.4981

zbMATH Keywords

latent variable modelsapproximate Bayesian computationintractable likelihoodgenerative modelssimulator-based models

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Bayesian inference (62F15) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Asymptotic Statistics
• Likelihood-free inference via classification
• Bayesian optimization for likelihood-free inference of simulator-based statistical models
• Simulation and the Asymptotics of Optimization Estimators
• Constructing Summary Statistics for Approximate Bayesian Computation: Semi-Automatic Approximate Bayesian Computation
• Title not available (Why is that?)
• Approximate Bayesian computational methods
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Title not available (Why is that?)
• A Method of Simulated Moments for Estimation of Discrete Response Models Without Numerical Integration
• Title not available (Why is that?)
• A user's guide to measure theoretic probability
• Encompassing and indirect inference
• Estimating the transmission dynamics of \textit{Streptococcus pneumoniae} from strain prevalence data
• Title not available (Why is that?)
• A tutorial on Bayesian models of perception
• The Poisson transform for unnormalised statistical models

Cited In (29)

• Likelihood-free inference by ratio estimation
• GADE: a generative adversarial approach to density estimation and its applications
• Likelihood-free inference via classification
• Variational Bayes with synthetic likelihood
• Efficient acquisition rules for model-based approximate Bayesian computation
• Likelihood-free inference in high dimensions with synthetic likelihood
• A likelihood-MPEC approach to target classification
• Metropolis–Hastings via Classification
• Approximate Bayesian computation via classification
• Bayesian inference of spreading processes on networks
• Inverse reinforcement learning from summary data
• Mining gold from implicit models to improve likelihood-free inference
• Parallel Gaussian process surrogate Bayesian inference with noisy likelihood evaluations
• Minimax confidence intervals for the sliced Wasserstein distance
• ABC of the future
• New approximate Bayesian computation algorithm for censored data
• Approximate Bayesian computation for the natural history of breast cancer, with application to data from a Milan cohort study
• Distance-learning for approximate Bayesian computation to model a volcanic eruption
• Robust Bayesian Synthetic Likelihood via a Semi-Parametric Approach
• Multimodal image synthesis with conditional implicit maximum likelihood estimation
• The frontier of simulation-based inference
• Local dimension reduction of summary statistics for likelihood-free inference
• Title not available (Why is that?)
• Title not available (Why is that?)
• Summary statistics and discrepancy measures for approximate Bayesian computation via surrogate posteriors
• Towards end‐to‐end likelihood‐free inference with convolutional neural networks
• Bayesian model-based clustering for longitudinal ordinal data
• Sequential Bayesian experimental design for implicit models via mutual information
• Classification by likelihood accordance functions

Uses Software

• abcrf

This page was built for publication: Likelihood-free inference via classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1702017)