REVIEW 10 cited by
Investigating the Impact of Model Misspecification in Neural Simulation-based Inference
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Investigating the Impact of Model Misspecification in Neural Simulation-based Inference
read the original abstract
Aided by advances in neural density estimation, considerable progress has been made in recent years towards a suite of simulation-based inference (SBI) methods capable of performing flexible, black-box, approximate Bayesian inference for stochastic simulation models. While it has been demonstrated that neural SBI methods can provide accurate posterior approximations, the simulation studies establishing these results have considered only well-specified problems -- that is, where the model and the data generating process coincide exactly. However, the behaviour of such algorithms in the case of model misspecification has received little attention. In this work, we provide the first comprehensive study of the behaviour of neural SBI algorithms in the presence of various forms of model misspecification. We find that misspecification can have a profoundly deleterious effect on performance. Some mitigation strategies are explored, but no approach tested prevents failure in all cases. We conclude that new approaches are required to address model misspecification if neural SBI algorithms are to be relied upon to derive accurate scientific conclusions.
Forward citations
Cited by 10 Pith papers
-
Mixed neural posterior estimation for simulators with discrete and continuous parameters
Extends NPE to mixed discrete-continuous parameter spaces via a factorized inference network combining an autoregressive classifier and generative model, trained jointly to yield accurate calibrated posteriors.
-
End-to-End Population Inference from Gravitational-Wave Strain using Transformers
Dingo-Pop uses a transformer to perform amortized, end-to-end population inference from GW strain data in seconds, bypassing per-event Monte Carlo sampling.
-
Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation
Introduces the first amortized neural posterior estimator conditioned on both data and temperature β for generalized Bayesian inference, matching MCMC performance on standard SBI benchmarks.
-
Neural Posterior Estimation for Inferring Weak Lensing Shear
Neural posterior estimation recovers accurate, well-calibrated constant-shear posteriors from simulated multiband images that include blending, variable PSFs, stars, and detector artifacts.
-
Towards Practical Field-Level Inference for Weak Lensing
Field-level inference from weak lensing maps yields significantly tighter cosmological constraints than power-spectrum analysis when using the same forward-modeling pipeline, especially on small scales.
-
Information-Preserving Domain Transfer with Unlabeled Data in Misspecified Simulation-Based Inference
SPIN performs bidirectional domain transfer in SBI to retain parameter mutual information from unlabeled real observations, improving real-world posterior inference under increasing misspecification.
-
Information-Preserving Domain Transfer with Unlabeled Data in Misspecified Simulation-Based Inference
SPIN improves posterior inference under model misspecification in SBI by learning parameter-relevant information-preserving domain transfers from unpaired unlabeled real-world data.
-
Flow Matching Calibration for Simulation-Based Inference under Model Misspecification
FMCPE trains a flow-matching correction that transports samples from a simulation-based posterior estimator toward the true posterior, using only tens to hundreds of ground-truth calibration pairs.
-
A Calibration Audit of a Gaia XP White-Dwarf Main-Sequence Binary Catalog: How Much BP-Band Residual it Takes to Manufacture Contamination
At the realistic ~2% local BP residual, injected contamination of a Gaia XP WD–MS binary selection is a null (spurious rate 0.08 on a 0.05 baseline); failure requires 10–20% local excess.
-
An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning
A structured introduction to ML-based simulation-based inference, contrasting Bayesian and frequentist frameworks and covering parameter inference, unfolding, and validation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.