REVIEW 5 cited by
LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and Cosmology
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
read the original abstract
This paper presents the Learning the Universe Implicit Likelihood Inference (LtU-ILI) pipeline, a codebase for rapid, user-friendly, and cutting-edge machine learning (ML) inference in astrophysics and cosmology. The pipeline includes software for implementing various neural architectures, training schemata, priors, and density estimators in a manner easily adaptable to any research workflow. It includes comprehensive validation metrics to assess posterior estimate coverage, enhancing the reliability of inferred results. Additionally, the pipeline is easily parallelizable and is designed for efficient exploration of modeling hyperparameters. To demonstrate its capabilities, we present real applications across a range of astrophysics and cosmology problems, such as: estimating galaxy cluster masses from X-ray photometry; inferring cosmology from matter power spectra and halo point clouds; characterizing progenitors in gravitational wave signals; capturing physical dust parameters from galaxy colors and luminosities; and establishing properties of semi-analytic models of galaxy formation. We also include exhaustive benchmarking and comparisons of all implemented methods as well as discussions about the challenges and pitfalls of ML inference in astronomical sciences. All code and examples are made publicly available at https://github.com/maho3/ltu-ili.
Forward citations
Cited by 5 Pith papers
-
Learning Cosmology from Nearest Neighbour Statistics
Nearest-neighbour distance maps, combined with kNN-CDFs in a hybrid neural network, constrain Ωm and σ8 from Quijote halos with R2=0.80 and 0.93, matching or beating point-cloud methods at a fraction of the compute.
-
DISCO-DJ II: a differentiable particle-mesh code for cosmology
A GPU-accelerated, differentiable particle-mesh N-body code achieves per-cent-level power-spectrum accuracy with few time steps and recovers sigma_8 plus initial conditions from a noisy mock field.
-
How does feedback affect the star formation histories of galaxies?
A unified empirical equation, fitted separately to three simulation suites, links galaxy star formation history shape to halo mass, baryon fraction, black hole mass, and feedback strength.
-
Learning at the Edge: Tailed-Uniform Sampling for Robust Simulation-Based Inference
Using a Tailed-Uniform proposal—uniform inside the prior box with Gaussian tails outside—reduces boundary errors in neural posterior estimation.
-
Implicit Likelihood Inference of the Neutrino Mass Hierarchy from Cosmological Data
A simulation-based neural-likelihood analysis of Planck 2018 and DESI DR2 data reports a weak preference (tilde_Delta = 0.12, 68% CL interval spanning both signs) for the normal neutrino mass hierarchy.
Discussion (0). Continue with ORCID to comment.