Learning from Topology: Cosmological Parameter Estimation from the Large-scale Structure

Abstract

The topology of the large-scale structure of the universe contains valuable information on the underlying cosmological parameters. While persistent homology can extract this topological information, the optimal method for parameter estimation from the tool remains an open question. To address this, we propose a neural network model to map persistence images to cosmological parameters. Through a parameter recovery test, we demonstrate that our model makes accurate and precise estimates, considerably outperforming conventional Bayesian inference approaches.

7 pages, 4 figures. Accepted to the Synergy of Scientific and Machine Learning Modeling Workshop (ICML 2023) and for publication in Machine Learning: Science and Technology

References in corpus (16)

• The Rockstar Phase-Space Temporal Halo Finder and the Velocity Offsets of Cluster Cores
• Chandra Cluster Cosmology Project III: Cosmological Parameter Constraints
• Why your model parameter confidences might be too optimistic -- unbiased estimation of the inverse covariance matrix
• The Quijote simulations
• FastPM: a new scheme for fast simulations of dark matter and halos
• On the assumption of Gaussianity for cosmological two-point statistics and parameter dependent covariance matrices
• The Zeldovich approximation: key to understanding Cosmic Web complexity
• Finding cosmic voids and filament loops using topological data analysis
• The Persistence of Large Scale Structures I: Primordial non-Gaussianity
• FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Persistent Homology and Non-Gaussianity
• Noise robustness of persistent homology on greyscale images, across filtrations and signatures
• Cosmology with Persistent Homology: a Fisher Forecast
• Quijote-PNG: Quasi-maximum likelihood estimation of Primordial Non-Gaussianity in the non-linear halo density field
• Differentiating small-scale subhalo distributions in CDM and WDM models using persistent homology

Cited by in corpus (1)

• Cosmology with Persistent Homology: Parameter Inference via Machine Learning