collaborators

15 papers

astro-ph.CO2026

MujicΛ: Reconstructing Initial Conditions from Incomplete Redshift Surveys with Projected Optimization

Chenze Dong, Benjamin Horowitz, Adrian E. Bayer +1

In this paper, we introduce MujicΛ (Mapping the Universe with Jax-based Initial Condition ReconstrΛction), an optimization-based framework for reconstructing initial conditions f…

astro-ph.CO2026

Field-Level Inference from Galaxies: BAO Reconstruction

Adrian E. Bayer, Liam Parker, David Valcin +3

Baryon acoustic oscillations (BAO) underpin the key cosmological results from modern spectroscopic galaxy surveys, but nonlinear gravitational evolution limits the precision achiev…

astro-ph.CO2026

Interpreting Cosmological Information from Neural Networks in the Hydrodynamic Universe

Arnab Lahiry, Adrian E. Bayer, Francisco Villaescusa-Navarro

What happens when a black box (neural network) meets a black box (simulation of the Universe)? Recent work has shown that convolutional neural networks (CNNs) can infer cosmologica…

astro-ph.IM2025

jFoF: GPU Cluster Finding with Gradient Propagation

Benjamin Horowitz, Adrian E. Bayer

We present jFoF, a fully GPU-native Friends-of-Friends (FoF) halo finder designed for both high-performance simulation analysis and differentiable modeling. Implemented in JAX, jFo…

astro-ph.CO2025

Impact of Simulation Box Size for Weak Lensing: Replication and Super-Sample Effects

Akira Tokiwa, Adrian E. Bayer, Joaquin Armijo +6

We quantify the bias caused by small simulation box size on weak lensing observables and covariances, considering both replication and super-sample effects for a range of higher-or…

cs.LG2025

CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning

Ningyuan Huang, Richard Stiskalek, Jun-Young Lee +6

Cosmological simulations provide a wealth of data in the form of point clouds and directed trees. A crucial goal is to extract insights from this data that shed light on the nature…