Papers

Improving Convolutional Neural Networks for Cosmological Fields with Random Permutation

K Zhong, M Gatti, B Jain - arXiv preprint arXiv:2403.01368, 2024 - arxiv.org
Astrophysics paper astro-ph.CO Suggest

… We use simulation-based inference (SBI) to show that the model outperforms CNN designs in the literature. We find a 30% improvement in the constraints of the 𝑆8 …

Link to paper

BibTeX

@article{2403.01368v1,
Author        = {Kunhao Zhong and Marco Gatti and Bhuvnesh Jain},
Title         = {Improving Convolutional Neural Networks for Cosmological Fields with Random Permutation},
Eprint        = {2403.01368v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {astro-ph.CO},
Abstract      = {Convolutional Neural Networks (CNNs) have recently been applied to cosmological fields -- weak lensing mass maps and galaxy maps. However, cosmological maps differ in several ways from the vast majority of images that CNNs have been tested on: they are stochastic, typically low signal-to-noise per pixel, and with correlations on all scales. Further, the cosmology goal is a regression problem aimed at inferring posteriors on parameters that must be unbiased. We explore simple CNN architectures and present a novel approach of regularization and data augmentation to improve its performance for lensing mass maps. We find robust improvement by using a mixture of pooling and shuffling of the pixels in the deep layers. The random permutation regularizes the network in the low signal-to-noise regime and effectively augments the existing data. We use simulation-based inference (SBI) to show that the model outperforms CNN designs in the literature. We find a 30% improvement in the constraints of the $S_8$ parameter for simulated Stage-III surveys, including systematic uncertainties such as intrinsic alignments. We explore various statistical errors corresponding to next-generation surveys and find comparable improvements. We expect that our approach will have applications to other cosmological fields as well, such as galaxy maps or 21-cm maps.},
Year          = {2024},
Month         = {Mar},
Url           = {http://arxiv.org/abs/2403.01368v1},
File          = {2403.01368v1.pdf}
}

Share