TY - JOUR

T1 - LINNA

T2 - Likelihood Inference Neural Network Accelerator

AU - To, Chun Hao

AU - Rozo, Eduardo

AU - Krause, Elisabeth

AU - Wu, Hao Yi

AU - Wechsler, Risa H

AU - Salcedo, Andrés N

N1 - Publisher Copyright:
© 2023 IOP Publishing Ltd and Sissa Medialab.

PY - 2023/1/1

Y1 - 2023/1/1

N2 - Bayesian posterior inference of modern multi-probe 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 wall-clock time that ranged from 1 to 21 days using a state-of-the-art computing cluster with 100 cores. These computational costs have severe environmental impacts and the long wall-clock 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 8-50. If applied to the first-year 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 CO2 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 first-year 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 multi-probe 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.

AB - Bayesian posterior inference of modern multi-probe 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 wall-clock time that ranged from 1 to 21 days using a state-of-the-art computing cluster with 100 cores. These computational costs have severe environmental impacts and the long wall-clock 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 8-50. If applied to the first-year 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 CO2 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 first-year 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 multi-probe 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.

KW - Bayesian reasoning

KW - cosmological parameters from LSS

KW - Machine learning

KW - Statistical sampling techniques

UR - http://www.scopus.com/inward/record.url?scp=85146500092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85146500092&partnerID=8YFLogxK

U2 - 10.1088/1475-7516/2023/01/016

DO - 10.1088/1475-7516/2023/01/016

M3 - Article

AN - SCOPUS:85146500092

SN - 1475-7516

VL - 2023

JO - Journal of Cosmology and Astroparticle Physics

JF - Journal of Cosmology and Astroparticle Physics

IS - 1

M1 - 016

ER -