Misspecification-robust Sequential Neural Likelihood for Simulation-based Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kelly, Ryan P., Nott, David J., Frazier, David T., Warne, David J., Drovandi, Chris
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917606857900032
author Kelly, Ryan P.
Nott, David J.
Frazier, David T.
Warne, David J.
Drovandi, Chris
author_facet Kelly, Ryan P.
Nott, David J.
Frazier, David T.
Warne, David J.
Drovandi, Chris
contents Simulation-based inference techniques are indispensable for parameter estimation of mechanistic and simulable models with intractable likelihoods. While traditional statistical approaches like approximate Bayesian computation and Bayesian synthetic likelihood have been studied under well-specified and misspecified settings, they often suffer from inefficiencies due to wasted model simulations. Neural approaches, such as sequential neural likelihood (SNL) avoid this wastage by utilising all model simulations to train a neural surrogate for the likelihood function. However, the performance of SNL under model misspecification is unreliable and can result in overconfident posteriors centred around an inaccurate parameter estimate. In this paper, we propose a novel SNL method, which through the incorporation of additional adjustment parameters, is robust to model misspecification and capable of identifying features of the data that the model is not able to recover. We demonstrate the efficacy of our approach through several illustrative examples, where our method gives more accurate point estimates and uncertainty quantification than SNL.
format Preprint
id arxiv_https___arxiv_org_abs_2301_13368
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Misspecification-robust Sequential Neural Likelihood for Simulation-based Inference
Kelly, Ryan P.
Nott, David J.
Frazier, David T.
Warne, David J.
Drovandi, Chris
Methodology
Machine Learning
Computation
Simulation-based inference techniques are indispensable for parameter estimation of mechanistic and simulable models with intractable likelihoods. While traditional statistical approaches like approximate Bayesian computation and Bayesian synthetic likelihood have been studied under well-specified and misspecified settings, they often suffer from inefficiencies due to wasted model simulations. Neural approaches, such as sequential neural likelihood (SNL) avoid this wastage by utilising all model simulations to train a neural surrogate for the likelihood function. However, the performance of SNL under model misspecification is unreliable and can result in overconfident posteriors centred around an inaccurate parameter estimate. In this paper, we propose a novel SNL method, which through the incorporation of additional adjustment parameters, is robust to model misspecification and capable of identifying features of the data that the model is not able to recover. We demonstrate the efficacy of our approach through several illustrative examples, where our method gives more accurate point estimates and uncertainty quantification than SNL.
title Misspecification-robust Sequential Neural Likelihood for Simulation-based Inference
topic Methodology
Machine Learning
Computation
url https://arxiv.org/abs/2301.13368