Machine learning constraints on deviations from general relativity from the large scale structure of the Universe

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