DeepAI AI Chat
Log In Sign Up

Likelihood-free MCMC with Approximate Likelihood Ratios

03/10/2019
by   Joeri Hermans, et al.
CERN
University of Liège
10

We propose a novel approach for posterior sampling with intractable likelihoods. This is an increasingly important problem in scientific applications where models are implemented as sophisticated computer simulations. As a result, tractable densities are not available, which forces practitioners to rely on approximations during inference. We address the intractability of densities by training a parameterized classifier whose output is used to approximate likelihood ratios between arbitrary model parameters. In turn, we are able to draw posterior samples by plugging this approximator into common Markov chain Monte Carlo samplers such as Metropolis-Hastings and Hamiltonian Monte Carlo. We demonstrate the proposed technique by fitting the generating parameters of implicit models, ranging from a linear probabilistic model to settings in high energy physics with high-dimensional observations. Finally, we discuss several diagnostics to assess the quality of the posterior.

READ FULL TEXT

page 7

page 8

04/04/2022

MCMC for GLMMs

Generalized linear mixed models (GLMMs) are often used for analyzing cor...
10/13/2020

Error-guided likelihood-free MCMC

This work presents a novel posterior inference method for models with in...
12/07/2020

Ratio of counts vs ratio of rates in Poisson processes

The often debated issue of `ratios of small numbers of events' is approa...
04/24/2020

Robust posterior inference when statistically emulating forward simulations

Scientific analyses often rely on slow, but accurate forward models for ...
10/15/2020

Sequential Likelihood-Free Inference with Implicit Surrogate Proposal

Bayesian inference without the access of likelihood, called likelihood-f...
08/30/2018

An Introduction to Inductive Statistical Inference -- from Parameter Estimation to Decision-Making

These lecture notes aim at a post-Bachelor audience with a backgound at ...
09/30/2015

Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets

Inference is typically intractable in high-treewidth undirected graphica...

Code Repositories

sbi

Simulation-based inference in PyTorch


view repo

lfi

Neural likelihood-free methods in PyTorch.


view repo