Pith. sign in

REVIEW 1 major objections 2 minor 6 cited by

FLAMINGO publicly releases over 2.3 petabytes of cosmological hydrodynamical simulation data with selective access tools.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-07-01 09:04 UTC pith:YDJMTMFJ

load-bearing objection This is a standard data-release paper for the FLAMINGO suite that makes 2.3 PB of calibrated hydro runs with neutrinos and varied feedback publicly accessible via a selective download service. the 1 major comments →

arxiv 2604.24324 v3 pith:YDJMTMFJ submitted 2026-04-27 astro-ph.CO

The FLAMINGO simulations data release

John C. Helly , Robert J. McGibbon , Joop Schaye , Matthieu Schaller , William McDonald , Joey Braspenning , Jeger C. Broxterman , Emily E. Costello
show 10 more authors
Willem Elbers Victor J. Forouhar Moreno Carlos S. Frenk Adrian Jenkins Roi Kugel Ian G. McCarthy Jaime Salcido Marcel P. van Daalen Bert Vandenbroucke Tianyi Yang
This is my paper
classification astro-ph.CO
keywords cosmological simulationshydrodynamical simulationsdata releasegalaxy formationAGN feedbackneutrino particleslarge-scale structure
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper describes the public release of more than 2.3 petabytes of outputs from the FLAMINGO suite. The data come from 22 hydrodynamical simulations that incorporate radiative cooling, star formation, chemical enrichment, supernova feedback, and two variants of AGN feedback, plus explicit neutrino particles. Sixteen gravity-only runs match the hydro initial conditions, including one with 10080 cubed particles. Products include snapshots, halo and galaxy catalogues, HEALPix lightcone maps, particle lightcone data, and power spectra. Simulations span three resolutions calibrated to the present-day galaxy stellar mass function and low-redshift cluster gas fractions, plus variants in cosmology, neutrino mass, and dark matter properties, all in 1 Gpc cubed volumes. A web service lets users browse and download subsets to address storage limits.

Core claim

The FLAMINGO data release makes available the full outputs of 22 hydrodynamical and 16 gravity-only cosmological simulations, including hitherto unpublished runs with extra dark matter particles, together with a web service that supports exploration and selective download of snapshots, catalogues, lightcone maps, and power spectra.

What carries the argument

The FLAMINGO suite of calibrated hydrodynamical simulations with explicit neutrinos and dual AGN feedback implementations, plus the web service for selective dataset access.

Load-bearing premise

The released data products accurately reflect the underlying simulation runs that were calibrated to the galaxy stellar mass function and cluster gas fractions.

What would settle it

A direct comparison showing whether the stellar mass functions or cluster gas fractions extracted from the released catalogues match the calibration targets used in the original runs.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Users can compare galaxy populations and cluster gas content across multiple resolutions and feedback variants without new runs.
  • Lightcone maps and power spectra enable direct tests against observational surveys of large-scale structure.
  • Variations in neutrino mass and dark matter nature allow exploration of cosmological parameter effects on structure formation.
  • The gravity-only counterparts support isolation of baryonic effects on halo properties.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The selective-download service may encourage similar access models for other petabyte-scale simulation releases.
  • Extra dark matter particle runs could be used to quantify resolution dependence of halo assembly histories beyond what the main suite provides.
  • The full set of lightcone outputs could support mock catalog generation for next-generation surveys.
  • Combining the released power spectra with the varied cosmologies offers a ready-made testbed for emulator construction.
  • keywords

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

1 major / 2 minor

Summary. The manuscript describes the public release of >2.3 petabytes of data from the FLAMINGO cosmological simulations. The suite includes 22 hydrodynamical simulations incorporating radiative cooling, star formation, chemical enrichment, supernova and AGN feedback, and explicit neutrino particles, plus 16 gravity-only runs (including a 10080^3-particle run) with matching initial conditions. Data products comprise snapshots, halo/galaxy catalogues, HEALPix lightcone maps, particle lightcone data, and power spectra. Simulations span three resolutions and vary the galaxy stellar mass function, cluster gas fractions, cosmology (including neutrino mass), and dark matter nature in 1 Gpc^3 volumes; fiducial runs are calibrated to the z=0 galaxy stellar mass function and low-redshift cluster gas fractions. Access is provided via full downloads and a selective web service.

Significance. If the released data products accurately match the described runs and calibration targets, the release constitutes a substantial community resource. The combination of large volumes, multiple resolutions, systematic parameter variations, and explicit neutrino/dark-matter variants enables direct tests of galaxy formation models, cosmological constraints, and alternative dark-matter scenarios that are otherwise computationally prohibitive for individual groups.

major comments (1)
  1. [Abstract] Abstract and § on calibration: the statement that the three fiducial resolutions 'have each been calibrated to reproduce the present-day galaxy stellar mass function and gas fractions in low-redshift clusters' is load-bearing for the scientific utility of the release, yet the manuscript provides neither the calibration procedure, the target observational datasets, nor quantitative validation metrics (e.g., χ^{2} values or residual plots). A reference to the companion methods paper is required for users to assess the fidelity of the released data.
minor comments (2)
  1. The text lists 22 hydrodynamical and 16 gravity-only runs but does not supply a compact table enumerating run names, particle numbers, box sizes, and varied parameters; such a table would improve usability.
  2. The description of the web service for selective downloads is brief; adding explicit limits on query size, supported formats, and example queries would clarify how the service mitigates the bandwidth/storage barrier mentioned in the abstract.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their positive assessment of the FLAMINGO data release manuscript and for the constructive comment. We address the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract and § on calibration: the statement that the three fiducial resolutions 'have each been calibrated to reproduce the present-day galaxy stellar mass function and gas fractions in low-redshift clusters' is load-bearing for the scientific utility of the release, yet the manuscript provides neither the calibration procedure, the target observational datasets, nor quantitative validation metrics (e.g., χ^{2} values or residual plots). A reference to the companion methods paper is required for users to assess the fidelity of the released data.

    Authors: We agree that the calibration details are important for users to assess the fidelity of the released data. The calibration procedure, target observational datasets (including the specific galaxy stellar mass function and cluster gas fraction measurements), and quantitative validation metrics are described in the companion methods paper. We will revise the manuscript to add an explicit citation to that companion paper in both the abstract and the section on the simulations. This will direct readers to the required information while keeping the data-release paper focused on its primary purpose. revision: yes

Circularity Check

0 steps flagged

No circularity: purely descriptive data-release paper

full rationale

The manuscript is a catalog of released simulation outputs (snapshots, catalogues, lightcones, power spectra) from the FLAMINGO suite. It states calibration targets and physics modules but advances no new equations, predictions, or fitted quantities presented as results. No derivation chain exists, so no step can reduce to its own inputs by construction, self-citation, or renaming. The central claim is simply that the listed data products are now publicly accessible.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a data-release description and introduces no new free parameters, axioms, or invented entities beyond those already present in the referenced simulations.

pith-pipeline@v0.9.1-grok · 5875 in / 1024 out tokens · 32149 ms · 2026-07-01T09:04:01.000400+00:00 · methodology

0 comments
read the original abstract

We describe the public release of $>2.3$ petabytes of data from the FLAMINGO cosmological simulations. The suite consists of hydrodynamical simulations that include radiative cooling, star formation, stellar mass loss and the resulting chemical enrichment, supernova feedback, and two implementations of AGN feedback. Neutrinos are simulated explicitly using particles. Data products include snapshots, halo and galaxy catalogues, HEALPix all-sky lightcone maps, particle data for lightcone maps, and power spectra. The FLAMINGO set includes 22 hydrodynamical simulations. In addition, there are 16 gravity-only simulations, including the $10080^3$ particles FLAMINGO-10k run, with initial conditions that match those of the corresponding hydrodynamical runs. The fiducial hydrodynamical simulations span three numerical resolutions that have each been calibrated to reproduce the present-day galaxy stellar mass function and gas fractions in low-redshift clusters. Other simulations systematically vary the galaxy stellar mass function, cluster gas fractions, cosmology (including neutrino masses), and/or the nature of dark matter, in volumes of 1Gpc$^3$. The release includes hitherto unpublished simulations that use extra dark matter particles. While we provide a facility for downloading complete simulation outputs, we recognise that for many users this will not be possible due to limited local storage or network bandwidth. We implement a web service that enables users to explore available outputs and selectively download datasets or parts of datasets.

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The limits of feedback from active galactic nuclei

    astro-ph.GA 2026-05 unverdicted novelty 6.0

    AGN feedback creates a mass-independent entropy ceiling that allows outflows to escape halos only below M_200m = 10^13.7 M_sun, explaining depleted gas in groups versus near-cosmic fractions in clusters.

  2. FLAMINGO: The thermal history of the Universe from tSZ effect cross-correlations and its dependencies on cosmology and baryon physics

    astro-ph.CO 2026-05 unverdicted novelty 6.0

    FLAMINGO simulations show tSZ cross-correlations scale as S8 to the power of about 3 and favor low S8=0.72 with strong feedback when compared to SDSS, BOSS, DES, and Planck data.

  3. FLAMINGO: The thermal history of the Universe from tSZ effect cross-correlations and its dependencies on cosmology and baryon physics

    astro-ph.CO 2026-05 conditional novelty 6.0

    tSZ cross-correlations with large-scale structure tracers prefer low S8 and strong baryonic feedback, yielding S8 = 0.72 and low group baryon fraction in FLAMINGO simulations.

  4. On the later evolution of observationally selected protocluster candidates at $z\,{\gtrsim}\,5$

    astro-ph.GA 2026-06 unverdicted novelty 5.0

    Simulations show observationally selected protocluster candidates at z ≳ 5 include significant interlopers, undergo 2-6 major mergers, and exhibit stronger clustering than observed, requiring total galaxy mass within ...

  5. Validation of the Hybrid Bias Expansion model for the galaxy bispectrum

    astro-ph.CO 2026-06 unverdicted novelty 5.0

    First systematic validation shows Hybrid Bias Expansion model for galaxy bispectrum remains accurate up to k=0.25 h/Mpc in DESI-like mocks, outperforming tree-level EFT.

  6. The local galaxy distribution does not violate the cosmological principle

    astro-ph.CO 2026-07 unverdicted novelty 3.0

    Correcting the comoving distance scale in DESI DR1 data eliminates apparent anisotropy, showing local galaxy distribution is consistent with ΛCDM expectations.

Reference graph

Works this paper leans on

38 extracted references · 10 canonical work pages · cited by 5 Pith papers · 5 internal anchors

  1. [1]

    Advanced Combustion System for High Efficiency(ACE)oftheNewSGT5/6-9000HLGasTurbine,

    Krebs, W., Schulz, A., Witzel, B., Johnson, C., Laster, W., Pent, J., Schilp, R., Wasif, S., and Weaver, A., 2022, “Advanced Combustion System for High Efficiency(ACE)oftheNewSGT5/6-9000HLGasTurbine,”TurboExpo: Power for Land, Sea, and Air, Vol. 86007, American Society of Mechanical Engineers, p. V03BT04A018, doi: 10.1115/GT2022-82299

    work page doi:10.1115/gt2022-82299 2022

  2. [2]

    Devel- opment of a Fuel Flexible H2-Natural Gas Gas Turbine Combustion Technology Platform,

    Witzel, B., Moëll, D., Parsania, N., Yilmaz, E., and Koenig, M., 2022, “Devel- opment of a Fuel Flexible H2-Natural Gas Gas Turbine Combustion Technology Platform,”TurboExpo: PowerforLand,Sea,andAir,Vol.86007,AmericanSo- cietyofMechanicalEngineers, p.V03BT04A036, doi:10.1115/GT2022-82881

    work page doi:10.1115/gt2022-82881 2022

  3. [3]

    Forrester, A., Sobester, A., and Keane, A., 2008,Engineering Design via Sur- rogate Modelling: a Practical Guide, John Wiley & Sons, UK

    2008

  4. [4]

    1, Springer, NY

    Santner, T.J., Williams, B.J., Notz, W.I., andWilliams, B.J., 2003,TheDesign and Analysis of Computer Experiments, Vol. 1, Springer, NY

    2003

  5. [5]

    12 of Engineering Applications of Computational Methods, Springer, Singapore

    Zhou, Q., Zhao, M., Hu, J., and Ma, M., 2022,Multi-Fidelity Surrogates: Modeling, Optimization and Applications, Vol. 12 of Engineering Applications of Computational Methods, Springer, Singapore

    2022

  6. [6]

    Groetsch, C. W. and Groetsch, C., 1993,Inverse Problems in the Mathematical Sciences, Vol. 52, Springer, Wiesbaden, Germany

    1993

  7. [7]

    Deep Unsupervised Learning Using Nonequilibrium Thermodynamics,

    Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., and Ganguli, S., 2015, “Deep Unsupervised Learning Using Nonequilibrium Thermodynamics,”Pro- ceedings of the 32nd International Conference on Machine Learning, Proceed- ings of Machine Learning Research, Vol. 37, PMLR, Lille, France, pp. 2256– 2265, https://proceedings.mlr.press/v37/sohl-dickstein15.html

    2015

  8. [8]

    Diffusion Models in Vision: A Survey,

    Croitoru, F., Hondru, V., Ionescu, R., and Shah, M., 2023, “Diffusion Models in Vision: A Survey,” IEEE Transactions on Pattern Analysis &; Machine Intelligence,45(09), pp. 10850–10869

    2023

  9. [9]

    In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

    Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B., 2022, “High-Resolution Image Synthesis with Latent Diffusion Models,”Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recog- nition, IEEE Computer Society, Los Alamitos, CA, USA, pp. 10684–10695, doi: 10.1109/CVPR52688.2022.01042

    work page doi:10.1109/cvpr52688.2022.01042 2022

  10. [10]

    Generative Adversarial Networks,

    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y., 2020, “Generative Adversarial Networks,” Communications of the ACM,63(11), pp. 139–144

    2020

  11. [11]

    Unsupervised Deep Learning for Super-Resolution Reconstruction of Turbulence,

    Kim, H., Kim, J., Won, S., and Lee, C., 2021, “Unsupervised Deep Learning for Super-Resolution Reconstruction of Turbulence,” Journal of Fluid Mechanics, 910, p. A29

    2021

  12. [12]

    Generative Modeling of Turbulence,

    Drygala, C., Winhart, B., di Mare, F., and Gottschalk, H., 2022, “Generative Modeling of Turbulence,” Physics of Fluids,34(3), p. 035114

    2022

  13. [13]

    A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications,

    Gui, J., Sun, Z., Wen, Y., Tao, D., and Ye, J., 2021, “A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications,” IEEE Transac- tions on Knowledge and Data Engineering,35(4), pp. 3313–3332

    2021

  14. [14]

    Neural Ordinary Differential Equations,

    Chen, R. T. Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D. K., 2018, “Neural Ordinary Differential Equations,”Advances in Neural Information Pro- cessing Systems, Vol. 31, Curran Associates, Inc., https://proceedings.neurips. cc/paper_files/paper/2018/file/69386f6bb1dfed68692a24c8686939b9-Paper.pdf

    2018

  15. [16]

    LU-Net: Invertible Neural Networks Based on Matrix Factorization,

    Chan, R., Penquitt, S., and Gottschalk, H., 2023, “LU-Net: Invertible Neural Networks Based on Matrix Factorization,” arXiv2302.10524, https://arxiv.org/ abs/2302.10524

    work page arXiv 2023

  16. [17]

    Comparison of Nonlinear to Linear Thermoacoustic StabilityAnalysisofaGasTurbineCombustionSystem,

    Krebs, W., Krediet, H., Portillo, E., Hermeth, S., Poinsot, T., Schimek, S., and Paschereit, O., 2013, “Comparison of Nonlinear to Linear Thermoacoustic StabilityAnalysisofaGasTurbineCombustionSystem,”J.ofEng.GasTurbines and Power,135(8), p. 081503

    2013

  17. [18]

    STAR-CCM+ User Guide Version 13.04,

    Siemens, 2019, “STAR-CCM+ User Guide Version 13.04,” Siemens PLM Soft- ware Inc

    2019

  18. [19]

    PredictionandMeasurementofThermoacousticImprovementsinGasTurbines with Annular Combustion Systems,

    Krüger, U., Hüren, J., Hoffmann, S., Krebs, W., Flohr, P., and Bohn, D., 2001, “PredictionandMeasurementofThermoacousticImprovementsinGasTurbines with Annular Combustion Systems,” J. Eng. Gas Turbines Power,123(3), pp. 557–566

    2001

  19. [20]

    Thermoacoustic StabilityChartforHighIntenseGasTurbineCombustionSystems,

    Krebs, W., Flohr, P., Prade, B., and Hoffmann, S., 2002, “Thermoacoustic StabilityChartforHighIntenseGasTurbineCombustionSystems,” Combustion Science and Technology,174(7), pp. 99–128

    2002

  20. [21]

    A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code,

    McKay, M. D., Beckman, R. J., and Conover, W. J., 2000, “A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code,” Technometrics, pp. 239–245

    2000

  21. [22]

    Guided Image Generation with Conditional Invertible Neural Networks

    Ardizzone, L., Lüth, C., Kruse, J., Rother, C., and Köthe, U., 2019, “Guided Image Generation with Conditional Invertible Neural Networks,”ArXiv e-prints, arXiv1907.02392, https://arxiv.org/abs/1907.02392

    work page internal anchor Pith review Pith/arXiv arXiv 2019

  22. [23]

    Glow: Generative Flow with Invert- ible 1x1 Convolutions,

    Kingma, D. P. and Dhariwal, P., 2018, “Glow: Generative Flow with Invert- ible 1x1 Convolutions,”Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R.Garnett,eds.,Vol.31,CurranAssociates,Inc.,https://proceedings.neurips.cc/ paper_files/paper/2018/file/d139db6a236200b21cc7f752979132d0-Paper.pdf

    2018

  23. [24]

    Universal Approximation Property of Invertible Neural Networks,

    Ishikawa, I., Teshima, T., Tojo, K., Oono, K., Ikeda, M., and Sugiyama, M., 2023, “Universal Approximation Property of Invertible Neural Networks,” Jour- nal of Machine Learning Research,24(287), pp. 1–68

    2023

  24. [25]

    Density estimation using Real NVP

    Dinh, L., Sohl-Dickstein, J., and Bengio, S., 2016, “Density Estimation using Real NVP,” arXiv preprint arXiv:1605.08803

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  25. [26]

    Normalizing Flows: An Introduction and Review of Current Methods,

    Kobyzev, I., Prince, S. J., and Brubaker, M. A., 2021, “Normalizing Flows: An Introduction and Review of Current Methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence,43(11), pp. 3964–3979

    2021

  26. [27]

    A Kernel Two-Sample Test,

    Gretton, A., Borgwardt, K. M., Rasch, M. J., Schölkopf, B., and Smola, A., 2012, “A Kernel Two-Sample Test,” Journal of Machine Learning Research, 13(25), pp. 723–773

    2012

  27. [28]

    Framework for Easily Invertible Architectures (FrEIA),

    Ardizzone, L., Bungert, T., Draxler, F., Köthe, U., Kruse, J., Schmier, R., and Sorrenson, P., 2018-2022, “Framework for Easily Invertible Architectures (FrEIA),” https://github.com/vislearn/FrEIA

    2018

  28. [29]

    Cognitron: A Self-Organizing Multilayered Neural Net- work,

    Fukushima, K., 1975, “Cognitron: A Self-Organizing Multilayered Neural Net- work,” Biological Cybernetics,20(3-4), pp. 121–136

    1975

  29. [30]

    Adam: A Method for Stochastic Optimization

    Kingma, D.P.andBa, J., 2017, “Adam: AMethodforStochasticOptimization,” arXiv1412.6980, https://arxiv.org/abs/1412.6980

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  30. [31]

    Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimiza- tion,

    Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., and Talwalkar, A., 2018, “Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimiza- tion,” Journal of Machine Learning Research,18(185), pp. 1–52

    2018

  31. [32]

    SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization,

    Lindauer, M., Eggensperger, K., Feurer, M., Biedenkapp, A., Deng, D., Ben- jamins, C., Ruhkopf, T., Sass, R., and Hutter, F., 2022, “SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization,” Journal of Machine Learning Research,23(54), pp. 1–9

    2022

  32. [33]

    Random Search for Hyper-Parameter Opti- mization,

    Bergstra, J. and Bengio, Y., 2012, “Random Search for Hyper-Parameter Opti- mization,” Journal of Machine Learning Research,13(10), pp. 281–305

    2012

  33. [34]

    A Simplex Method for Function Minimiza- tion,

    Nelder, J. A. and Mead, R., 1965, “A Simplex Method for Function Minimiza- tion,” The Computer Journal,7(4), pp. 308–313

    1965

  34. [35]

    Mode Collapse in Generative Adversarial Networks: An Overview,

    Kossale, Y., Airaj, M., and Darouichi, A., 2022, “Mode Collapse in Generative Adversarial Networks: An Overview,”2022 8th Interna- tional Conference on Optimization and Applications (ICOA), pp. 1–6, doi: 10.1109/ICOA55659.2022.9934291

    work page doi:10.1109/icoa55659.2022.9934291 2022

  35. [36]

    Analyzing Inverse Problems with Invertible Neural Networks

    Ardizzone, L., Kruse, J., Wirkert, S., Rahner, D., Pellegrini, E. W., Klessen, R. S., Maier-Hein, L., Rother, C., and Köthe, U., 2019, “Analyzing Inverse Problems with Invertible Neural Networks,”ArXiv e-prints, arXiv1808.04730, https://arxiv.org/abs/1808.04730

    work page internal anchor Pith review Pith/arXiv arXiv 2019

  36. [37]

    Im- proving Language Understanding by Generative Pre-Training,

    Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al., 2018, “Im- proving Language Understanding by Generative Pre-Training,” OpenAI, San Francisco, CA, USA

    2018

  37. [38]

    NICE: Non-linear Independent Components Estimation

    Dinh, L., Krueger, D., and Bengio, Y., 2015, “NICE: Non-linear Independent Components Estimation,” 1410.8516, https://arxiv.org/abs/1410.8516

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  38. [39]

    Variational Inference with Normalizing Flows,

    Rezende, D. and Mohamed, S., 2015, “Variational Inference with Normalizing Flows,”Proceedings of the 32nd International Conference on Machine Learn- ing, F. Bach and D. Blei, eds., Proceedings of Machine Learning Research, Vol. 37, PMLR, Lille, France, pp. 1530–1538, https://proceedings.mlr.press/ v37/rezende15.html 12 /GTP-24-1269Transactions of the ASME...

    2015