Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks

TL;DR

This paper compares Bayesian Neural Network models for estimating cosmological parameters from CMB data, demonstrating Flipout's superior performance and showing how BNNs can accelerate MCMC convergence and improve parameter constraints.

Contribution

It introduces a comprehensive comparison of BNN sampling methods for CMB parameter estimation and provides a practical guide for training multi-channel BNNs with reliable uncertainty estimates.

Findings

Flipout outperforms other BNN sampling methods.

BNNs provide faster inference than MCMC, enabling better initial proposals.

Combining polarization data with temperature improves parameter constraints.

Abstract

In this paper, we present the first study that compares different models of Bayesian Neural Networks (BNNs) to predict the posterior distribution of the cosmological parameters directly from the Cosmic Microwave Background temperature and polarization maps. We focus our analysis on four different methods to sample the weights of the network during training: Dropout, DropConnect, Reparameterization Trick (RT), and Flipout. We find out that Flipout outperforms all other methods regardless of the architecture used, and provides tighter constraints for the cosmological parameters. Moreover we compare with MCMC posterior analysis obtaining comparable error correlation among parameters, with BNNs being orders of magnitude faster in inference, although less accurate. Thanks to the speed of the inference process with BNNs, the posterior distribution, outcome of the neural network, can be used as the initial proposal for the Markov Chain. We show that this combined approach increases the acceptance rate in the Metropolis-Hasting algorithm and accelerates the convergence of the MCMC, while reaching the same final accuracy. In the second part of the paper, we present a guide to the training and calibration of a successful multi-channel BNN for the CMB temperature and polarization map. We show how tuning the regularization parameter for the standard deviation of the approximate posterior on the weights in Flipout and RT we can produce unbiased and reliable uncertainty estimates, i.e., the regularizer acts like a hyperparameter analogous to the dropout rate in Dropout. Finally, we show how polarization, when combined with the temperature in a unique multi-channel tensor fed to a single BNN, helps to break degeneracies among parameters and provides stringent constraints.