REVIEW 7 cited by
Automatic physical inference with information maximising neural networks
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
Automatic physical inference with information maximising neural networks
read the original abstract
Compressing large data sets to a manageable number of summaries that are informative about the underlying parameters vastly simplifies both frequentist and Bayesian inference. When only simulations are available, these summaries are typically chosen heuristically, so they may inadvertently miss important information. We introduce a simulation-based machine learning technique that trains artificial neural networks to find non-linear functionals of data that maximise Fisher information: information maximising neural networks (IMNNs). In test cases where the posterior can be derived exactly, likelihood-free inference based on automatically derived IMNN summaries produces nearly exact posteriors, showing that these summaries are good approximations to sufficient statistics. In a series of numerical examples of increasing complexity and astrophysical relevance we show that IMNNs are robustly capable of automatically finding optimal, non-linear summaries of the data even in cases where linear compression fails: inferring the variance of Gaussian signal in the presence of noise; inferring cosmological parameters from mock simulations of the Lyman-{\alpha} forest in quasar spectra; and inferring frequency-domain parameters from LISA-like detections of gravitational waveforms. In this final case, the IMNN summary outperforms linear data compression by avoiding the introduction of spurious likelihood maxima. We anticipate that the automatic physical inference method described in this paper will be essential to obtain both accurate and precise cosmological parameter estimates from complex and large astronomical data sets, including those from LSST and Euclid.
Forward citations
Cited by 7 Pith papers
-
KiDS+VIKING-450 cosmology with Bayesian hierarchical model redshift distributions
Bayesian hierarchical modeling of photometric redshifts in KiDS+VIKING-450 raises S8 to 0.756 ± 0.039 and reduces Planck tension to 1.9σ.
-
Cosmology with Multi-Wavelength Line Intensity Mapping Synergies in the SKAO Era
Reviews how cross-correlating SKAO 21-cm LIM with other lines like [CII], CO, and Ly-alpha can mitigate systematics, enhance sensitivity, and disentangle cosmological from astrophysical parameters.
-
Cosmology with Intensity Mapping via Statistics Beyond the Power Spectrum in the SKAO Era
Reviews multiple higher-order statistics for 21-cm intensity mapping and forecasts their detectability with SKAO, incorporating noise and foreground effects.
-
High-Redshift Signatures from the Cosmic Dawn and the Epoch of Reionization
A review chapter summarizing theoretical 21-cm signatures from Cosmic Dawn and Reionization and their detectability with SKA-Low.
-
Inferring Cosmology and Astrophysics from the High-redshift 21cm Signal with SKA-Low
A review chapter on tools for inferring galaxy and IGM properties from the 21 cm signal using the initial SKA-Low array configuration.
-
Overview of 21cm Experiments at high redshift with SKAO
Overview of SKA-Low 21cm experiments for high-redshift cosmology, covering power spectra, tomography, 21cm forest, cross-correlations, and key telescope features.
-
Overview of 21cm Experiments at high redshift with SKAO
An overview summarizing SKA-Low 21cm experiments for power spectrum, tomography, 21-cm forest, and cross-correlations, plus critical telescope features, building on the 2015 SKA Science Book.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.