# Machine Learning Constraints on Deviations from General Relativity from the Large Scale Structure of the Universe

Published in *Physical Review D*, 2022

# Abstract

We use a particular machine learning approach, called the genetic algorithms (GAs), in order to place constraints on deviations from general relativity (GR) via a possible evolution of Newton’s constant μ=G_{eff}/G_{N} and of the dark energy anisotropic stress η, both defined to be equal to one in GR. Specifically, we use a plethora of background and linear-order perturbations data, such as Type Ia supernovae, baryon acoustic oscillations, cosmic chronometers, redshift space distortions, and E_{g} data. We find that although the GA is affected by the lower quality of the currently available data, especially from the E_{g} data, the reconstruction of Newton’s constant is consistent with a constant value within the errors. On the other hand, the anisotropic stress deviates strongly from unity due to the sparsity and the systematics of the E_{g} data. Finally, we also create synthetic data based on a next-generation survey and forecast the limits of any possible detection of deviations from GR. In particular, we use two fiducial models: one based on the cosmological constant ΛCDM model and another on a model with an evolving Newton’s constant, dubbed μCDM. We find that the GA reconstructions of μ(z) and η(z) can be constrained to within a few percent of the fiducial models and in the case of the μCDM mocks, they can also provide a strong detection of several σs, thus demonstrating the utility of the GA reconstruction approach.

# Cite

If you use any of the above codes or the figures in a published work please cite the following paper: *Machine Learning Constraints on Deviations from General Relativity from the Large Scale Structure of the Universe.*

George Alestas, Lavrentios Kazantzidis and Savvas Nesseris

Phys.Rev.D 106 (2022) 10, 10, arxiv:2209.12799.

Any further questions/comments are welcome.

# Authors Lists

George Alestas - g.alestas@csic.es

Lavrentios Kazantzidis - l.c.kazantzidis@gmail.com

Savvas Nesseris - savvas.nesseris@csic.es