Uncertainty Quantification of the Virial Black Hole Mass with Conformal Prediction

• URL: http://arxiv.org/abs/2307.04993v1
• Date: Tue, 11 Jul 2023 03:13:25 GMT
• Title: Uncertainty Quantification of the Virial Black Hole Mass with Conformal Prediction
• Authors: Suk Yee Yong and Cheng Soon Ong
• Abstract summary: We propose the application of quantalised quantile regression to quantify the uncertainties of the black hole predictions in a machine learning setting. We show that the CQR method provides prediction intervals that adjust to the black hole mass and its related properties. Using a combination of neural network model and CQR framework, the recovered virial black hole mass predictions and uncertainties are comparable to those measured from the Sloan Digital Sky Survey.
• Score: 6.487663563916903
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Precise measurements of the black hole mass are essential to gain insight on the black hole and host galaxy co-evolution. A direct measure of the black hole mass is often restricted to nearest galaxies and instead, an indirect method using the single-epoch virial black hole mass estimation is used for objects at high redshifts. However, this method is subjected to biases and uncertainties as it is reliant on the scaling relation from a small sample of local active galactic nuclei. In this study, we propose the application of conformalised quantile regression (CQR) to quantify the uncertainties of the black hole predictions in a machine learning setting. We compare CQR with various prediction interval techniques and demonstrated that CQR can provide a more useful prediction interval indicator. In contrast to baseline approaches for prediction interval estimation, we show that the CQR method provides prediction intervals that adjust to the black hole mass and its related properties. That is it yields a tighter constraint on the prediction interval (hence more certain) for a larger black hole mass, and accordingly, bright and broad spectral line width source. Using a combination of neural network model and CQR framework, the recovered virial black hole mass predictions and uncertainties are comparable to those measured from the Sloan Digital Sky Survey. The code is publicly available at https://github.com/yongsukyee/uncertain_blackholemass.

Related papers

• Inclusive reactions from finite Minkowski spacetime correlation functions [44.99833362998488]
  We use real-time methods to determine scattering amplitudes of few-hadron systems for arbitrary kinematics. In units of the lightest mass of the theory, we find that to constrain amplitudes using real-time methods within $mathcalO(10%)$, the spacetime volumes must satisfy $mL sim mathcalO(10-102)$ and $ mTsim mathcalO(102-104)$.
  arXiv  Detail & Related papers  (2024-06-11T01:39:24Z)
• Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise [51.87307904567702]
  Quantile regression is a leading approach for obtaining such intervals via the empirical estimation of quantiles in the distribution of outputs. We propose Relaxed Quantile Regression (RQR), a direct alternative to quantile regression based interval construction that removes this arbitrary constraint. We demonstrate that this added flexibility results in intervals with an improvement in desirable qualities.
  arXiv  Detail & Related papers  (2024-06-05T13:36:38Z)
• Information Theoretical Approach to Detecting Quantum Gravitational Corrections [0.0]
  We calculate the Kullback-Leibler divergence for the probability distributions obtained from the Parikh-Wilczek formalism. We observe that the quantum gravitational corrections increase the Kullback-Leibler divergence as the mass of the black hole decreases. After a certain critical value, quantum gravitational corrections tend to decrease again as the mass of the black hole decreases.
  arXiv  Detail & Related papers  (2023-10-19T16:32:53Z)
• Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference [59.040209568168436]
  We first generate a rapid proposal for the Bayesian posterior using neural networks, and then attach importance weights based on the underlying likelihood and prior. This provides (1) a corrected posterior free from network inaccuracies, (2) a performance diagnostic (the sample efficiency) for assessing the proposal and identifying failure cases, and (3) an unbiased estimate of the Bayesian evidence. We carry out a large study analyzing 42 binary black hole mergers observed by LIGO and Virgo with the SEOBNRv4PHM and IMRPhenomHMXP waveform models.
  arXiv  Detail & Related papers  (2022-10-11T18:00:02Z)
• Inferring Structural Parameters of Low-Surface-Brightness-Galaxies with Uncertainty Quantification using Bayesian Neural Networks [70.80563014913676]
  We show that a Bayesian Neural Network (BNN) can be used for the inference, with uncertainty, of such parameters from simulated low-surface-brightness galaxy images. Compared to traditional profile-fitting methods, we show that the uncertainties obtained using BNNs are comparable in magnitude, well-calibrated, and the point estimates of the parameters are closer to the true values.
  arXiv  Detail & Related papers  (2022-07-07T17:55:26Z)
• Dense Uncertainty Estimation [62.23555922631451]
  In this paper, we investigate neural networks and uncertainty estimation techniques to achieve both accurate deterministic prediction and reliable uncertainty estimation. We work on two types of uncertainty estimations solutions, namely ensemble based methods and generative model based methods, and explain their pros and cons while using them in fully/semi/weakly-supervised framework.
  arXiv  Detail & Related papers  (2021-10-13T01:23:48Z)
• AGNet: Weighing Black Holes with Deep Learning [2.4522011090845846]
  Supermassive black holes (SMBHs) are ubiquitously found at the centers of most massive galaxies. Traditional methods require spectroscopic data which is expensive to gather. We present an algorithm that weighs SMBHs using quasar light time series.
  arXiv  Detail & Related papers  (2021-08-17T16:45:11Z)
• Understanding the Under-Coverage Bias in Uncertainty Estimation [58.03725169462616]
  quantile regression tends to emphunder-cover than the desired coverage level in reality. We prove that quantile regression suffers from an inherent under-coverage bias. Our theory reveals that this under-coverage bias stems from a certain high-dimensional parameter estimation error.
  arXiv  Detail & Related papers  (2021-06-10T06:11:55Z)
• Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes [17.145373200662277]
  We present a method that reconstructs the AGN time series and simultaneously infers the posterior probability density distribution. This work is the first to address probabilistic time series reconstruction and parameter inference for AGN in an end-to-end fashion.
  arXiv  Detail & Related papers  (2021-06-02T20:17:31Z)
• Constraining the Generalized Uncertainty Principle with the light twisted by rotating black holes and M87* [0.0]
  We test the validity of the Generalized Heisenberg's Uncertainty principle in the presence of strong gravitational fields nearby rotating black holes. We find from numerical simulations a relationship between the spectrum of the orbital angular momentum of light and the corrections needed to formulate the Generalized Uncertainty Principle. We obtain more precise limits from the experimental data of M87*, confirming the validity of scenarios compatible with General Relativity.
  arXiv  Detail & Related papers  (2021-03-25T11:06:55Z)
• AGNet: Weighing Black Holes with Machine Learning [2.598391092244943]
  Supermassive black holes (SMBHs) are ubiquitously found at the centers of most galaxies. Traditional methods require spectral data which is expensive to gather. We present an algorithm that weighs SMBHs using quasar light time series.
  arXiv  Detail & Related papers  (2020-11-30T18:30:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.