Bayesian technique to combine independently-trained Machine-Learning models applied to direct dark matter detection

Abstract

We carry out a Bayesian analysis of dark matter (DM) direct detection data to determine particle model parameters using the Truncated Marginal Neural Ratio Estimation (TMNRE) machine learning technique. TMNRE avoids an explicit calculation of the likelihood, which instead is estimated from simulated data, unlike in traditional Markov Chain Monte Carlo (MCMC) algorithms. This considerably speeds up, by several orders of magnitude, the computation of the posterior distributions, which allows to perform the Bayesian analysis of an otherwise computationally prohibitive number of benchmark points. In this article we demonstrate that, in the TMNRE framework, it is possible to include, combine, and remove different datasets in a modular fashion, which is fast and simple as there is no need to re-train the machine learning algorithm or to define a combined likelihood. In order to assess the performance of this method, we consider the case of WIMP DM with spin-dependent and independent interactions with protons and neutrons in a xenon experiment. After validating our results with MCMC, we employ the TMNRE procedure to determine the regions where the DM parameters can be reconstructed. Finally, we present CADDENA, a Python package that implements the modular Bayesian analysis of direct detection experiments described in this work.

Version published in JCAP. Discussions expanded and references added. 27 pages, 8 figures, 2 tables

References in corpus (55)

• Particle Dark Matter: Evidence, Candidates and Constraints
• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• Multimodal nested sampling: an efficient and robust alternative to MCMC methods for astronomical data analysis
• Bilby: A user-friendly Bayesian inference library for gravitational-wave astronomy
• Importance Nested Sampling and the MultiNest Algorithm
• First Dark Matter Search Results from the LUX-ZEPLIN (LZ) Experiment
• Implication of neutrino backgrounds on the reach of next generation dark matter direct detection experiments
• Direct Detection of Sub-GeV Dark Matter
• The Effective Field Theory of Dark Matter Direct Detection
• Dark Matter Search Results from the PandaX-4T Commissioning Run
• First Dark Matter Search with Nuclear Recoils from the XENONnT Experiment
• SENSEI: Direct-Detection Results on sub-GeV Dark Matter from a New Skipper-CCD
• DARWIN: towards the ultimate dark matter detector
• Annual Modulation of Dark Matter: A Review
• Model-independent WIMP Scattering Responses and Event Rates: A Mathematica Package for Experimental Analysis
• Constraints on Light Dark Matter Particles Interacting with Electrons from DAMIC at SNOLAB
• Projected WIMP Sensitivity of the XENONnT Dark Matter Experiment
• First germanium-based constraints on sub-MeV Dark Matter with the EDELWEISS experiment
• Large-scale nuclear structure calculations for spin-dependent WIMP scattering with chiral effective field theory currents
• Fog on the horizon: a new definition of the neutrino floor for direct dark matter searches
• Search for dark matter with a 231-day exposure of liquid argon using DEAP-3600 at SNOLAB
• Approximating Likelihood Ratios with Calibrated Discriminative Classifiers
• First Constraints from DAMIC-M on Sub-GeV Dark-Matter Particles Interacting with Electrons
• Complementarity of Dark Matter Direct Detection Targets
• Nuclear structure aspects of spin-independent WIMP scattering off xenon
• Astrophysical uncertainties on the local dark matter distribution and direct detection experiments
• Three-year annual modulation search with COSINE-100
• Uncertainties in the Galactic dark matter distribution: an update
• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• CYGNUS: Feasibility of a nuclear recoil observatory with directional sensitivity to dark matter and neutrinos
• Snowmass2021 Cosmic Frontier: The landscape of low-threshold dark matter direct detection in the next decade
• Dark Matter vs. Neutrinos: The effect of astrophysical uncertainties and timing information on the neutrino floor
• Convolutional Neural Networks for Direct Detection of Dark Matter
• A Direct Detection View of the Neutrino NSI Landscape
• Sensitivity of future liquid argon dark matter search experiments to core-collapse supernova neutrinos
• An induced annual modulation signature in COSINE-100 data by DAMA/LIBRA's analysis method
• Complementarity of dark matter direct detection: the role of bolometric targets
• Review on dark matter searches
• Light Dark Matter Constraints from SuperCDMS HVeV Detectors Operated Underground with an Anticoincidence Event Selection
• WimPyDD: an object-oriented Python code for the calculation of WIMP direct detection signals
• A semi-supervised approach to dark matter searches in direct detection data with machine learning
• Sampling-Based Accuracy Testing of Posterior Estimators for General Inference
• Opening the energy window on direct dark matter detection
• Improving ANAIS-112 sensitivity to DAMA/LIBRA signal with machine learning techniques
• Towards an automated data cleaning with deep learning in CRESST
• Fast and Flexible Analysis of Direct Dark Matter Search Data with Machine Learning
• A New Method for Analysing Dark Matter Direct Detection Data
• Improved Sensitivity of the DRIFT-IId Directional Dark Matter Experiment using Machine Learning
• A machine learning-based methodology for pulse classification in dual-phase xenon time projection chambers
• DarkSide-20k: Next generation Direct Dark Matter searches with liquid Argon
• Deep learning for Directional Dark Matter search
• Machine-learning techniques applied to three-year exposure of ANAIS-112
• Effective Field Theory Analysis of CDMSlite Run 2 Data
• A Strategy for Low-Mass Dark Matter Searches with Cryogenic Detectors in the SuperCDMS SNOLAB Facility
• Fast Bayesian Inference for Neutrino Non-Standard Interactions at Dark Matter Direct Detection Experiments

Cited by in corpus (3)

• Insights into Dark Matter Direct Detection Experiments: Decision Trees versus Deep Learning
• Information-theoretic astrophysical uncertainties in the effective theory of dark matter direct detection
• Dark Matter profiles of "in silico" galaxies: deep learning inference