Robust Neural Network-Enhanced Estimation of Local Primordial Non-Gaussianity

Abstract

When applied to the non-linear matter distribution of the universe, neural networks have been shown to be very statistically sensitive probes of cosmological parameters, such as the linear perturbation amplitude ${\sigma }_8$. However, when used as a "black box", neural networks are not robust to baryonic uncertainty. We propose a robust architecture for constraining primordial non-Gaussianity $f_{NL}$, by training a neural network to locally estimate ${\sigma }_8$, and correlating these local estimates with the large-scale density field. We apply our method to N-body simulations, and show that $\sigma (f_{NL})$ is 3.5 times better than the constraint obtained from a standard halo-based approach. We show that our method has the same robustness property as large-scale halo bias: baryonic physics can change the normalization of the estimated $f_{NL}$, but cannot change whether $f_{NL}$ is detected.

References in corpus (7)

• Array Programming with NumPy
• The imprints of primordial non-gaussianities on large-scale structure: scale dependent bias and abundance of virialized objects
• Measuring primordial non-gaussianity without cosmic variance
• Going Beyond the Galaxy Power Spectrum: an Analysis of BOSS Data with Wavelet Scattering Transforms
• Learning cosmology and clustering with cosmic graphs
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Extracting cosmological parameters from N-body simulations using machine learning techniques

Cited by in corpus (5)

• Learning to Concentrate: Multi-tracer Forecasts on Local Primordial Non-Gaussianity with Machine-Learned Bias
• Quijote-PNG: Quasi-maximum likelihood estimation of Primordial Non-Gaussianity in the non-linear halo density field
• Capturing primordial non-Gaussian signatures in the late Universe by multi-scale extrema of the cosmic log-density field
• Inferring Cosmological Parameters on SDSS via Domain-Generalized Neural Networks and Lightcone Simulations
• Constraining $f_{NL}$ using the Large-Scale Modulation of Small-Scale Statistics