Paper
Emulation of SPHEREx Galaxy Power Spectra I: Neural Network Details and Optimization
Authors
Joseph Adamo, Grace Gibbins, Anne Moore, Tim Eifler
Abstract
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.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.16003v1</id>\n <title>Emulation of SPHEREx Galaxy Power Spectra I: Neural Network Details and Optimization</title>\n <updated>2026-03-16T23:23:36Z</updated>\n <link href='https://arxiv.org/abs/2603.16003v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.16003v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='astro-ph.CO'/>\n <published>2026-03-16T23:23:36Z</published>\n <arxiv:comment>10 pages, 7 figures, submitted to Physical Review D</arxiv:comment>\n <arxiv:primary_category term='astro-ph.CO'/>\n <author>\n <name>Joseph Adamo</name>\n </author>\n <author>\n <name>Grace Gibbins</name>\n </author>\n <author>\n <name>Anne Moore</name>\n </author>\n <author>\n <name>Tim Eifler</name>\n </author>\n </entry>"
}