Saved in:
Bibliographic Details
Main Authors: Adamo, Joseph, Gibbins, Grace, Moore, Anne, Eifler, Tim
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.16003
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918398760321024
author Adamo, Joseph
Gibbins, Grace
Moore, Anne
Eifler, Tim
author_facet Adamo, Joseph
Gibbins, Grace
Moore, Anne
Eifler, Tim
contents We present neural networks to generate redshift-space galaxy power spectrum multipoles for multiple tracer and redshift bins simultaneously given a set of input cosmology and galaxy bias parameters. This emulator utilizes a combination of fully-connected layers and transformer architecture to accurately predict galaxy power spectrum multipoles $900$ times faster than the SPHEREx pipeline. We quantify network performance using both $Δχ^2$, and likelihood contours for simulated SPHEREx analyses, using two correlated tracer bins and two independent redshift bins. After optimizing network architecture, the loss function, and training set sampling strategy, we achieve $\operatorname{Med}\left( Δχ^2\right) = 0.069$ when comparing to our testing set. At the contour-level our emulator agrees with EFT predictions over a realistic parameter range, with an average 1D best-fit shift of $0.078σ$ and $0.82 \%$ change in 1D error bars. These results demonstrate the feasibility of using neural-network emulators to accelerate SPHEREx redshift-space power-spectrum analyses.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16003
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Emulation of SPHEREx Galaxy Power Spectra I: Neural Network Details and Optimization
Adamo, Joseph
Gibbins, Grace
Moore, Anne
Eifler, Tim
Cosmology and Nongalactic Astrophysics
We present neural networks to generate redshift-space galaxy power spectrum multipoles for multiple tracer and redshift bins simultaneously given a set of input cosmology and galaxy bias parameters. This emulator utilizes a combination of fully-connected layers and transformer architecture to accurately predict galaxy power spectrum multipoles $900$ times faster than the SPHEREx pipeline. We quantify network performance using both $Δχ^2$, and likelihood contours for simulated SPHEREx analyses, using two correlated tracer bins and two independent redshift bins. After optimizing network architecture, the loss function, and training set sampling strategy, we achieve $\operatorname{Med}\left( Δχ^2\right) = 0.069$ when comparing to our testing set. At the contour-level our emulator agrees with EFT predictions over a realistic parameter range, with an average 1D best-fit shift of $0.078σ$ and $0.82 \%$ change in 1D error bars. These results demonstrate the feasibility of using neural-network emulators to accelerate SPHEREx redshift-space power-spectrum analyses.
title Emulation of SPHEREx Galaxy Power Spectra I: Neural Network Details and Optimization
topic Cosmology and Nongalactic Astrophysics
url https://arxiv.org/abs/2603.16003