Extensive Studies of the Neutron Star Equation of State from the Deep Learning Inference with the Observational Data Augmentation
arXiv:2101.08156 · doi:10.1007/JHEP03(2021)273
Abstract
We discuss deep learning inference for the neutron star equation of state (EoS) using the real observational data of the mass and the radius. We make a quantitative comparison between the conventional polynomial regression and the neural network approach for the EoS parametrization. For our deep learning method to incorporate uncertainties in observation, we augment the training data with noise fluctuations corresponding to observational uncertainties. Deduced EoSs can accommodate a weak first-order phase transition, and we make a histogram for likely first-order regions. We also find that our observational data augmentation has a byproduct to tame the overfitting behavior. To check the performance improved by the data augmentation, we set up a toy model as the simplest inference problem to recover a double-peaked function and monitor the validation loss. We conclude that the data augmentation could be a useful technique to evade the overfitting without tuning the neural network architecture such as inserting the dropout.
45 pages, 25 figures
References in corpus (21)
- Shapiro delay measurement of a two solar mass neutron star
- A Massive Pulsar in a Compact Relativistic Binary
- PSR J0030+0451 Mass and Radius from NICER Data and Implications for the Properties of Neutron Star Matter
- A NICER View of PSR J0030+0451: Millisecond Pulsar Parameter Estimation
- Tidal Love numbers of neutron stars
- Cold Quark Matter
- Neutron matter at next-to-next-to-next-to-leading order in chiral effective field theory
- Astrophysical Measurement of the Equation of State of Neutron Star Matter
- Sound velocity bound and neutron stars
- A NICER view of PSR J0030+0451: Implications for the dense matter equation of state
- Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
- Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects
- Spectral Representations of Neutron-Star Equations of State
- Nuclear equation of state for core-collapse supernova simulations with realistic nuclear forces
- Compact stars with sequential QCD phase transitions
- Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
- Was GW170817 a canonical neutron star merger? Bayesian analysis with a third family of compact stars
- Hard-core deconfinement and soft-surface delocalization from nuclear to quark matter
- Functional renormalization group studies of nuclear and neutron matter
- Neural networks reconstruction of the dense-matter equation of state from neutron-star parameters
- Parameter estimates in binary black hole collisions using neural networks
Cited by in corpus (36)
- Machine Learning in Nuclear Physics
- Trace anomaly as signature of conformality in neutron stars
- Exploring QCD matter in extreme conditions with Machine Learning
- Precision Studies of QCD in the Low Energy Domain of the EIC
- Bayesian analysis of neutron-star properties with parameterized equations of state: the role of the likelihood functions
- Inference of the sound speed and related properties of neutron stars
- Gravitational Wave Signal for Quark Matter with Realistic Phase Transition
- Phase Transition Phenomenology with Nonparametric Representations of the Neutron Star Equation of State
- Neural network reconstruction of the dense matter equation of state from neutron star observables
- Reconstructing the neutron star equation of state from observational data via automatic differentiation
- Momentum Shell in Quarkyonic Matter from Explicit Duality: A Dual Model for Cold, Dense QCD
- Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
- Translating neutron star observations to nuclear symmetry energy via artificial neural networks
- Equation of state of cold and dense QCD matter in resummed perturbation theory
- Extracting nuclear matter properties from the neutron star matter equation of state using deep neural networks
- Dense Matter in Neutron Stars with eXTP
- Deducing Neutron Star Equation of State Parameters Directly From Telescope Spectra with Uncertainty-Aware Machine Learning
- Decoding Neutron Star Observations: Revealing Composition through Bayesian Neural Networks
- Nonparametric model for the equations of state of neutron star from deep neural network
- From NS observations to nuclear matter properties: a machine learning approach
- Analyzing the speed of sound in neutron star with machine learning
- Neural Simulation-Based Inference of the Neutron Star Equation of State directly from Telescope Spectra
- Do we need dense matter equation of state in curved spacetime for neutron stars?
- Hybrid stars with large quark cores within the parity doublet model and modified NJL model
- Realizing the potential of deep neural network for analyzing neutron star observables and dense matter equation of state
- Signature of hadron-quark crossover in binary-neutron-star mergers
- Deep learning inference of the neutron star equation of state
- Mass and tidal parameter extraction from gravitational waves of binary neutron stars mergers using deep learning
- Explainable autoencoder for neutron star dense matter parameter estimation
- Detecting Hyperons in neutron stars -- a machine learning approach
- Direct nonparametric multimessenger constraints on the equation of state of cold dense nuclear matter
- Conditional variational autoencoder inference of neutron star equation of state from astrophysical observations
- Nuclear mass table in density functional approach inspired by neutron-star observations
- Properties of the Object HESS J1731-347 as a Twin Compact Star
- Anisotropic pressure effect on central EOS of PSR J0740+6620 in the light of dimensionless TOV equation
- Theory progress at Strange Quark Matter 2021