CoChat
Sign Up
Cited by 128Cosmology and Gravitation TheoriesGalaxies: Formation, Evolution, PhenomenaDark Matter and Cosmic Phenomena

Non-Gaussian information from weak lensing data via deep learning

Open access
Gupta, Arushi, Matilla, José Manuel Zorrilla, Hsu, Daniel, Haiman, Zoltán·2018·Physical Review D
DOI 10.1103/physrevd.97.103515
Open this paper in CoChat — free accountOpen PDF

Abstract

Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and apply a two-dimensional convolutional neural network to simulated noiseless lensing maps covering 96 different cosmological models over a range of ${{\mathrm{\ensuremath{\Omega}}}_{m},{\ensuremath{\sigma}}_{8}}$. Using the area of the confidence contour in the ${{\mathrm{\ensuremath{\Omega}}}_{m},{\ensuremath{\sigma}}_{8}}$ plane as a figure of merit, derived from simulated convergence maps smoothed on a scale of 1.0 arcmin, we show that the neural network yields $\ensuremath{\approx}5\ifmmode\times\else\texttimes\fi{}$ tighter constraints than the power spectrum, and $\ensuremath{\approx}4\ifmmode\times\else\texttimes\fi{}$ tighter than the lensing peaks. Such gains illustrate the extent to which weak lensing data encode cosmological information not accessible to the power spectrum or even other, non-Gaussian statistics such as lensing peaks.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1103/physrevd.97.103515

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • All these papers reported the ability to extract more information than a 2pt function analysis, even on realistically noisy data.

    “With this approach, all these papers reported the ability to extract more information than a 2pt function analysis, even on realistically noisy data”

    From The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys (2023) · cites this paper as Gupta et al. 2018

    The Conclusions (p. 11) report that the neural network outperformed the power spectrum, a two-point statistic, on simulated noiseless weak-lensing maps. They explicitly say whether the improvement holds for more realistic, noisy data remains an open question, so this paper does not support the noisy-data part of the claim. (LLM, conf=0.93)

    Experimental — accuracy not yet measured

  • The output of a CNN trained for regression is not an unbiased estimator for cosmological parameters, but should be interpreted as a low-dimensional summary statistic for inference in a second step.

    “It is important to note, as reported in all these papers, that the output of the network trained for regression will not be an unbiased estimator for the cosmological parameters, but should be interpreted as a low-dimensional summary statistic, which can then be used for inference in a second step, independent from the network training.”

    From The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys (2023) · cites this paper as Gupta et al. 2018

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 57 references couldn’t be matched to a known paper.

Research works printed but not linked: 5

  1. M. Takada, 2015, Statistical Challenges in 21st Century Cosmology, IAU Symposium
  2. S. Ravanbakhsh, 2016, Proceedings of the 33rd International Conference on Machine Learning
  3. A. L. Maas, 2013, Proceedings of a International Conference on Machine Learning
  4. C. Zhang, 2017, International Conference on Learning Representations
  5. J. Herault, 1985, Proceedings of the 10th GRETSI symposium on signal and image processing

Cited by

Sorted by citations

Related

Authors
Gupta, A., Matilla, J. M. Z., Hsu, D., & Haiman, Z.
Affiliations
Columbia University (US)
ORCID
Venue
Physical Review D
Publisher
American Physical Society (APS)
Published
2018-05-18
Volume
97
Issue
10
ISSN
  • 2470-0010 (ISSN-L)
  • 2470-0029
DOI
10.1103/physrevd.97.103515
OpenAlex
W2787427854
Cited by
128
References
57
Citations by year
2026: 7 · 2025: 14 · 2024: 14 · 2023: 13 · 2022: 18 · 2021: 17 · 2020: 15 · 2019: 23 · 2018: 7
FWCI
8.34
Type
journal article
Language
en
Open access
Licence
Locations
  • Physical review. D/Physical review. D. (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Science Foundation (ACI-1053575, AST-1210877)
  • Alfred P. Sloan Foundation
  • Simons Foundation
  • Institute for Data Sciences and Engineering
Topics
  • Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Cosmology and Gravitation Theories
  • Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Galaxies: Formation, Evolution, Phenomena
  • Physical Sciences › Physics and Astronomy › Nuclear and High Energy Physics › Dark Matter and Cosmic Phenomena
Keywords
weak gravitational lensing, non-Gaussian statistics, convolutional neural networks, cosmological parameter constraints, matter density parameter, amplitude of matter fluctuations, convergence maps, power spectrum comparison

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review