2022

Amortized Bayesian Inference for Supernovae in the Era of the Vera Rubin Observatory Using Normalizing Flows

Villar, V. Ashley

Understand

The Vera Rubin Observatory, set to begin observations in mid-2024, will increase our discovery rate of supernovae to well over one million annually.

There has been a significant push to develop new methodologies to identify, classify and ultimately understand the millions of supernovae discovered with the Rubin Observatory.
Here, we present the first simulation-based inference method using normalizing flows, trained to rapidly infer the parameters of toy supernovae model in multivariate, Rubin-like datastreams.
We find that our method is well-calibrated compared to traditional inference methodologies (specifically MCMC), requiring only one-ten-thousandth of the CPU hours during test time.

Built on

W. D. Arnett, “Type i supernovae. i-analytic solutions for the early part of the light curve,” The Astrophysical Journal , vol. 253, pp. 785–797, 1982
1982
Earlier work this paper cites.
E. Chatzopoulos, J. C. Wheeler, and J. Vinko, “Generalized semi-analytical models of supernova light curves,” The Astrophysical Journal , vol. 746, no. 2, p. 121, 2012
2012
Earlier work this paper cites.
D. Foreman-Mackey, D. W. Hogg, D. Lang, and J. Goodman, “emcee: the mcmc hammer,” Publications of the Astronomical Society of the Pacific , vol. 125, no. 925, p. 306, 2013
2013
Earlier work this paper cites.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv e-prints , p. arXiv:1412.6980, Dec. 2014
Original
2014
Earlier work this paper cites.
D. Rezende and S. Mohamed, “Variational inference with normalizing flows,” in International conference on machine learning . PMLR, 2015, pp. 1530–1538
2015
Earlier work this paper cites.
M. Germain, K. Gregor, I. Murray, and H. Larochelle, “MADE: Masked Autoencoder for Distribution Estimation,” arXiv e-prints , p. arXiv:1502.03509, Feb. 2015
Original
2015
Earlier work this paper cites.

Similar

G. Papamakarios, T. Pavlakou, and I. Murray, “Masked autoregressive flow for density estimation,” Advances in neural information processing systems , vol. 30, 2017
2017
Cited alongside, same era.
V. A. Villar, E. Berger, B. D. Metzger, and J. Guillochon, “Theoretical models of optical transients. i. a broad exploration of the duration–luminosity phase space,” The Astrophysical Journal , vol. 849, no. 1, p. 70, 2017
2017
Cited alongside, same era.
M. L. Graham, A. J. Connolly, Ž. Ivezić, S. J. Schmidt, R. L. Jones, M. Jurić, S. F. Daniel, and P. Yoachim, “Photometric redshifts with the lsst: evaluating survey observing strategies,” The Astronomical Journal , vol. 155, no. 1, p. 1, 2017
2017
Cited alongside, same era.
M. Lochner, D. M. Scolnic, H. Awan, N. Regnault, P. Gris, R. Mandelbaum, E. Gawiser, H. Almoubayyed, C. N. Setzer, S. Huber et al. , “Optimizing the lsst observing strategy for dark energy science: Desc recommendations for the wide-fast-deep survey,” arXiv preprint arXiv:1812.00515 , 2018
Original
2018
Cited alongside, same era.
K. Boone, “Avocado: Photometric classification of astronomical transients with gaussian process augmentation,” The Astronomical Journal , vol. 158, no. 6, p. 257, 2019
2019
Cited alongside, same era.
S. R. Green, C. Simpson, and J. Gair, “Gravitational-wave parameter estimation with autoregressive neural network flows,” Physical Review D , vol. 102, no. 10, p. 104057, 2020
2020
Cited alongside, same era.
A. Sánchez, G. Cabrera, P. Huijse, and F. Förster, “Amortized variational inference for type ia supernova light curves.”
Cited in the paper.

Then

H. J. Hortúa, L. Malagò, and R. Volpi, “Constraining the reionization history using bayesian normalizing flows,” Machine Learning: Science and Technology , vol. 1, no. 3, p. 035014, 2020
2020
Later among the works it cites.
V. A. Villar, G. Hosseinzadeh, E. Berger, M. Ntampaka, D. O. Jones, P. Challis, R. Chornock, M. R. Drout, R. J. Foley, R. P. Kirshner et al. , “Superraenn: A semisupervised supernova photometric classification pipeline trained on pan-starrs1 medium-deep survey supernovae,” The Astrophysical Journal , vol. 905, no. 2, p. 94, 2020
2020
Later among the works it cites.
V. A. Villar, M. Cranmer, G. Contardo, S. Ho, and J. Y.-Y. Lin, “Anomaly detection for multivariate time series of exotic supernovae,” arXiv preprint arXiv:2010.11194 , 2020
Original
2020
Later among the works it cites.
A. Tejero-Cantero, J. Boelts, M. Deistler, J.-M. Lueckmann, C. Durkan, P. J. Gonçalves, D. S. Greenberg, and J. H. Macke, “sbi: A toolkit for simulation-based inference,” Journal of Open Source Software , vol. 5, no. 52, p. 2505, 2020. [Online]. Available: https://doi.org/10.21105/joss.02505
2020
Later among the works it cites.
H. Qu, M. Sako, A. Möller, and C. Doux, “Scone: Supernova classification with a convolutional neural network,” The Astronomical Journal , vol. 162, no. 2, p. 67, 2021
2021
Later among the works it cites.
C. Hahn and P. Melchior, “Accelerated bayesian sed modeling using amortized neural posterior estimation,” arXiv preprint arXiv:2203.07391 , 2022
Original
2022
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…