Pith. sign in

REVIEW 2 cited by

Truncated Marginal Neural Ratio Estimation

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

arxiv 2107.01214 v2 pith:SJ2CXVQN submitted 2021-07-02 stat.ML astro-ph.IMcs.LGhep-ph

classification stat.MLastro-ph.IMcs.LGhep-ph
keywords inferencealgorithmmarginalposteriorposteriorsefficiencyefficientempirical
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Parametric stochastic simulators are ubiquitous in science, often featuring high-dimensional input parameters and/or an intractable likelihood. Performing Bayesian parameter inference in this context can be challenging. We present a neural simulation-based inference algorithm which simultaneously offers simulation efficiency and fast empirical posterior testability, which is unique among modern algorithms. Our approach is simulation efficient by simultaneously estimating low-dimensional marginal posteriors instead of the joint posterior and by proposing simulations targeted to an observation of interest via a prior suitably truncated by an indicator function. Furthermore, by estimating a locally amortized posterior our algorithm enables efficient empirical tests of the robustness of the inference results. Since scientists cannot access the ground truth, these tests are necessary for trusting inference in real-world applications. We perform experiments on a marginalized version of the simulation-based inference benchmark and two complex and narrow posteriors, highlighting the simulator efficiency of our algorithm as well as the quality of the estimated marginal posteriors.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Sequential simulation-based inference for extreme mass ratio inspirals

    gr-qc 2025-05 conditional novelty 6.0 of 10

    Sequential simulation-based inference with truncated marginal neural ratio estimation shrinks the 11-parameter search volume for simulated non-spinning extreme-mass-ratio inspirals by factors of 1e6 to 1e7 and recover...

  2. Simulation-based inference on warm dark matter from HERA forecasts

    astro-ph.CO 2024-12 conditional novelty 5.0 of 10

    Using neural ratio estimation on mock HERA power spectra, the authors forecast 95% lower bounds on the thermal WDM mass that exceed the 5.3 keV Lyman-alpha limit when the galaxy threshold mass Mturn is below 1e8 M_sun.

Pith tools