Data Compression and Inference in Cosmology with Self-Supervised Machine Learning

Abstract

The influx of massive amounts of data from current and upcoming cosmological surveys necessitates compression schemes that can efficiently summarize the data with minimal loss of information. We introduce a method that leverages the paradigm of self-supervised machine learning in a novel manner to construct representative summaries of massive datasets using simulation-based augmentations. Deploying the method on hydrodynamical cosmological simulations, we show that it can deliver highly informative summaries, which can be used for a variety of downstream tasks, including precise and accurate parameter inference. We demonstrate how this paradigm can be used to construct summary representations that are insensitive to prescribed systematic effects, such as the influence of baryonic physics. Our results indicate that self-supervised machine learning techniques offer a promising new approach for compression of cosmological data as well its analysis.

17 + 6 pages, 12 + 6 figures; replaced to match version accepted by MNRAS

References in corpus (41)

• Array Programming with NumPy
• Measuring and testing dependence by correlation of distances
• Improved Baselines with Momentum Contrastive Learning
• Simulating galaxy formation with black hole driven thermal and kinetic feedback
• The DESI Experiment Part I: Science,Targeting, and Survey Design
• Simba: Cosmological Simulations with Black Hole Growth and Feedback
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
• Modelling baryonic feedback for survey cosmology
• A Cookbook of Self-Supervised Learning
• A new approach to observational cosmology using the scattering transform
• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• Nuisance hardened data compression for fast likelihood-free inference
• Towards an Optimal Estimation of Cosmological Parameters with the Wavelet Scattering Transform
• The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
• Massive data compression for parameter-dependent covariance matrices
• Joint analysis of anisotropic power spectrum, bispectrum and trispectrum: application to N-body simulations
• Going Beyond the Galaxy Power Spectrum: an Analysis of BOSS Data with Wavelet Scattering Transforms
• Large Synoptic Survey Telescope: Dark Energy Science Collaboration
• Robust Field-level Likelihood-free Inference with Galaxies
• The Cosmic Graph: Optimal Information Extraction from Large-Scale Structure using Catalogues
• How much a galaxy knows about its large-scale environment?: An information theoretic perspective
• Precise and Accurate Cosmology with CMBxLSS Power Spectra and Bispectra
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• A robust estimator of mutual information for deep learning interpretability
• Capturing the physics of MaNGA galaxies with self-supervised Machine Learning
• Neural networks as optimal estimators to marginalize over baryonic effects
• It takes two to know one: Computing accurate one-point PDF covariances from effective two-point PDF models
• Sufficiency of a Gaussian power spectrum likelihood for accurate cosmology from upcoming weak lensing surveys
• Understanding and Improving the Role of Projection Head in Self-Supervised Learning
• Towards Good Practices in Self-supervised Representation Learning
• The CAMELS project: Expanding the galaxy formation model space with new ASTRID and 28-parameter TNG and SIMBA suites
• To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review
• Variational Inference for Deblending Crowded Starfields
• For self-supervised learning, Rationality implies generalization, provably
• Sensitivity Analysis of Simulation-Based Inference for Galaxy Clustering
• On the nature of disks at high redshift seen by JWST/CEERS with contrastive learning and cosmological simulations
• Evaluating Summary Statistics with Mutual Information for Cosmological Inference
• Radio Galaxy Zoo: Towards building the first multi-purpose foundation model for radio astronomy with self-supervised learning
• An information-based metric for observing strategy optimization, demonstrated in the context of photometric redshifts with applications to cosmology
• Detecting Galaxy Tidal Features Using Self-Supervised Representation Learning

Cited by in corpus (10)

• EFTofLSS meets simulation-based inference: ${\sigma }_8$ from biased tracers
• Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models
• Explaining dark matter halo density profiles with neural networks
• Simulation-Based Inference Benchmark for Weak Lensing Cosmology
• A field-level emulator for modified gravity
• SKATR: A Self-Supervised Summary Transformer for SKA
• Data-Space Validation of High-Dimensional Models by Comparing Sample Quantiles
• Classification of Radio Sources Through Self-Supervised Learning
• Kilonova Light Curve Parameter Estimation Using Likelihood-Free Inference
• Skew-spectra: a generalization to spin-$s$