OL\'E -- Online Learning Emulation in Cosmology

Abstract

In this work, we present OL\'E, a new online learning emulator for use in cosmological inference. The emulator relies on Gaussian Processes and Principal Component Analysis for efficient data compression and fast evaluation. Moreover, OL\'E features an automatic error estimation for optimal active sampling and online learning. All training data is computed on-the-fly, making the emulator applicable to any cosmological model or dataset. We illustrate the emulator's performance on an array of cosmological models and data sets, showing significant improvements in efficiency over similar emulators without degrading accuracy compared to standard theory codes. We find that OL\'E is able to considerably speed up the inference process, increasing the efficiency by a factor of $30-350$, including data acquisition and training. Typically the runtime of the likelihood code becomes the computational bottleneck. Furthermore, OL\'E emulators are differentiable; we demonstrate that, together with the differentiable likelihoods available in the $\texttt{candl}$ library, we can construct a gradient-based sampling method which yields an additional improvement factor of 4. OL\'E can be easily interfaced with the popular samplers $\texttt{MontePython}$ and $\texttt{Cobaya}$, and the Einstein-Boltzmann solvers $\texttt{CLASS}$ and $\texttt{CAMB}$. OL\'E is publicly available at https://github.com/svenguenther/OLE .