Measuring the Dark Matter Self-Interaction Cross-Section with Deep Compact Clustering for Robust Machine Learning Inference

Abstract

We have developed a machine learning algorithm capable of detecting ``out-of-domain data'' for trustworthy cosmological inference. By using data from two separate suites of cosmological simulations, we show that our algorithm is able to determine whether ``observed'' data is consistent with its training domain, returning confidence estimates as well as accurate parameter estimations. We apply our algorithm to two-dimensional images of galaxy clusters from the BAHAMAS-SIDM and DARKSKIES simulations with the aim to measure the self-interaction cross-section of dark matter. Through deep compact clustering we construct an informative latent space where galaxy clusters are mapped to the latent space forming ``latent-clusters'' for each simulation, with the location of the latent-cluster corresponding to the macroscopic parameters, such as the cross-section, ${\sigma }_{\mathrm{DM}}/m$. We then pass through mock observations, where the location of the observed latent-cluster informs us of which properties are shared with the training data. If the observed latent-cluster shares no similarities with latent-clusters from the known simulations, we can conclude that our simulations do not represent the observations and discard any parameter estimations, thus providing us with a method to measure machine learning confidence. This method serves as a blueprint for transparent and robust inference that is in demand in scientific machine learning.

11 pages, 7 figures, submitted to A&A

References in corpus (20)

• Nine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Parameter Results
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• A direct empirical proof of the existence of dark matter
• Observational evidence for self-interacting cold dark matter
• Halo Formation in Warm Dark Matter Models
• A measurement of the cosmological mass density from clustering in the 2dF Galaxy Redshift Survey
• Cosmological Simulations with Self-Interacting Dark Matter II: Halo Shapes vs. Observations
• The BAHAMAS project: Calibrated hydrodynamical simulations for large-scale structure cosmology
• The unexpected diversity of dwarf galaxy rotation curves
• Towards a realistic population of simulated galaxy groups and clusters
• What does the Bullet Cluster tell us about self-interacting dark matter?
• Mass and magnification maps for the Hubble Space Telescope Frontier Fields clusters: implications for high redshift studies
• Lens models and magnification maps of the six Hubble Frontier Fields clusters
• Observable tests of self-interacting dark matter in galaxy clusters: cosmological simulations with SIDM and baryons
• In the Wake of Dark Giants: New Signatures of Dark Matter Self Interactions in Equal Mass Mergers of Galaxy Clusters
• Velocity-dependent Self-interacting Dark Matter from Groups and Clusters of Galaxies
• Observable tests of self-interacting dark matter in galaxy clusters: BCG wobbles in a constant density core
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• On the dissection of degenerate cosmologies with machine learning
• Euclid preparation. XLIII. Measuring detailed galaxy morphologies for Euclid with machine learning