Single frequency CMB B-mode inference with realistic foregrounds from a single training image

Abstract

With a single training image and using wavelet phase harmonic augmentation, we present polarized Cosmic Microwave Background (CMB) foreground marginalization in a high-dimensional likelihood-free (Bayesian) framework. We demonstrate robust foreground removal using only a single frequency of simulated data for a BICEP-like sky patch. Using Moment Networks we estimate the pixel-level posterior probability for the underlying {E,B} signal and validate the statistical model with a quantile-type test using the estimated marginal posterior moments. The Moment Networks use a hierarchy of U-Net convolutional neural networks. This work validates such an approach in the most difficult limiting case: pixel-level, noise-free, highly non-Gaussian dust foregrounds with a single training image at a single frequency. For a real CMB experiment, a small number of representative sky patches would provide the training data required for full cosmological inference. These results enable robust likelihood-free, simulation-based parameter and model inference for primordial B-mode detection using observed CMB polarization data.

Accepted by Monthly Notices of the Royal Astronomical Society Letters. 5 pages with 3 figures (plus 1 page of Supporting Materials with 2 figures)

References in corpus (3)

• Fast likelihood-free cosmology with neural density estimators and active learning
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• A new approach for the statistical denoising of Planck interstellar dust polarization data

Cited by in corpus (13)

• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• Non-Gaussian modelling and statistical denoising of Planck dust polarization full-sky maps using scattering transforms
• CENN: A fully convolutional neural network for CMB recovery in realistic microwave sky simulations
• Scattering Spectra Models for Physics
• A hybrid map-$C_{\ell }$ component separation method for primordial CMB $B$-mode searches
• Generative models of astrophysical fields with scattering transforms on the sphere
• Generative Models of Multi-channel Data from a Single Example -- Application to Dust Emission
• Inference of the optical depth to reionization $\tau$ from $\text{Planck}$ CMB maps with convolutional neural networks
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery
• Deep Needlet: A CNN based full sky component separation method in Needlet space
• From few to many maps: A fast map-level emulator for extreme augmentation of CMB systematics datasets
• Map Reconstruction of radio observations with Conditional Invertible Neural Networks
• Bayesian imaging inverse problem with scattering transform