Hybrid summary statistics: neural weak lensing inference beyond the power spectrum
T. Lucas Makinen, Alan Heavens, Natalia Porqueres, and 3 more authors
Journal of Cosmology and Astroparticle Physics, Jan 2025
Cosmological inference relies on compressed forms of the raw data for analysis, with traditional methods exploiting physics knowledge to define summary statistics, such as power spectra, that are known to capture much of the information. An alternative approach is to ask a neural network to find a set of informative summary statistics from data, which can then be analysed either by likelihood- or simulation-based inference. This has the advantage that for non-Gaussian fields, they may capture more information than two-point statistics. However, a disadvantage is that the network almost certainly relearns that two-point statistics are informative. In this paper, we introduce a new hybrid method, which combines the best of both: we use our domain knowledge to define informative physics-based summary statistics, and explicitly ask the network to augment the set with extra statistics that capture information that is not already in the existing summaries. This yields a new, general loss formalism that reduces both the number of simulations and network size needed to extract useful non-Gaussian information from cosmological fields, and guarantees that the resulting summary statistics are at least as informative as the power spectrum. In combination, they can then act as powerful inputs to implicit inference of model parameters. We use a generalisation of Information Maximising Neural Networks (IMNNs) to obtain the extra summaries, and obtain parameter constraints from simulated tomographic weak gravitational lensing convergence maps. We study several dark matter simulation resolutions in low- and high-noise regimes. We show that i) the information-update formalism extracts at least 3× and up to 8× as much information as the angular power spectrum in all noise regimes, ii) the network summaries are highly complementary to existing 2-point summaries, and iii) our formalism allows for networks with extremely lightweight architectures to match much larger regression networks with far fewer simulations needed to obtain asymptotically optimal inference.
The Degeneracy Distillery2026
Dark Energy Survey Year 3 results: optimized wCDM simulation-based inference with weak lensing map-level hybrid statistics2026
Hybrid summary statistics: neural weak lensing inference beyond the power spectrumJournal of Cosmology and Astroparticle Physics, Jan 2025
Fishnets: Information-Optimal, Scalable Aggregation for Sets and GraphsJan 2024
Hybrid Summary StatisticsJan 2024
Exoplanet atmosphere evolution: emulation with neural networksMonthly Notices of the Royal Astronomical Society, Mar 2023
Field-level inference of cosmic shear with intrinsic alignments and baryonsarXiv e-prints, Apr 2023
The Cosmic Graph: Optimal Information Extraction from Large-Scale Structure using CataloguesThe Open Journal of Astrophysics, Dec 2022
Lossless, scalable implicit likelihood inference for cosmological fieldsJournal of Cosmology and Astroparticle Physics, Nov 2021
deep21: a deep learning method for 21 cm foreground removalJournal of Cosmology and Astroparticle Physics, Apr 2021
