LINNA: Likelihood Inference Neural Network Accelerator
Abstract
Bayesian posterior inference of modern multiprobe cosmological analyses incurs massive computational costs. For instance, depending on the combinations of probes, a single posterior inference for the Dark Energy Survey (DES) data had a wallclock time that ranged from 1 to 21 days using a stateoftheart computing cluster with 100 cores. These computational costs have severe environmental impacts and the long wallclock time slows scientific productivity. To address these difficulties, we introduce LINNA: the Likelihood Inference Neural Network Accelerator. Relative to the baseline DES analyses, LINNA reduces the computational cost associated with posterior inference by a factor of 850. If applied to the firstyear cosmological analysis of Rubin Observatory's Legacy Survey of Space and Time (LSST Y1), we conservatively estimate that LINNA will save more than U.S. $300,000 on energy costs, while simultaneously reducing CO_{2} emission by 2,400 tons. To accomplish these reductions, LINNA automatically builds training data sets, creates neural network emulators, and produces a Markov chain that samples the posterior. We explicitly verify that LINNA accurately reproduces the firstyear DES (DES Y1) cosmological constraints derived from a variety of different data vectors with our default code settings, without needing to retune the algorithm every time. Further, we find that LINNA is sufficient for enabling accurate and efficient sampling for LSST Y10 multiprobe analyses. We make LINNA publicly available at https://github.com/chto/linna, to enable others to perform fast and accurate posterior inference in contemporary cosmological analyses.
 Publication:

Journal of Cosmology and Astroparticle Physics
 Pub Date:
 January 2023
 DOI:
 10.1088/14757516/2023/01/016
 arXiv:
 arXiv:2203.05583
 Bibcode:
 2023JCAP...01..016T
 Keywords:

 Bayesian reasoning;
 Machine learning;
 Statistical sampling techniques;
 cosmological parameters from LSS;
 Astrophysics  Cosmology and Nongalactic Astrophysics;
 Astrophysics  Instrumentation and Methods for Astrophysics
 EPrint:
 21 pages, 12 figures, submitted to JCAP, comments are welcome