François Lanusse

selected publications

1. 

   The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data

   The Multimodal Universe Collaboration, Jeroen Audenaert, Micah Bowles, and 26 more authors

   arXiv e-prints Dec 2024

   Abs arXiv Bib Blog

   We present the MULTIMODAL UNIVERSE, a large-scale multimodal dataset of scientific astronomical data, compiled specifically to facilitate machine learning research. Overall, the MULTIMODAL UNIVERSE contains hundreds of millions of astronomical observations, constituting 100 TB of multi-channel and hyper-spectral images, spectra, multivariate time series, as well as a wide variety of associated scientific measurements and “metadata”. In addition, we include a range of benchmark tasks representative of standard practices for machine learning methods in astrophysics. This massive dataset will enable the development of large multi-modal models specifically targeted towards scientific applications. All codes used to compile the MULTIMODAL UNIVERSE and a description of how to access the data is available at https://github.com/MultimodalUniverse/MultimodalUniverse

   @article{2024arXiv241202527T,
     adsnote = {Provided by the SAO/NASA Astrophysics Data System},
     adsurl = {https://ui.adsabs.harvard.edu/abs/2024arXiv241202527T},
     archiveprefix = {arXiv},
     author = {{The Multimodal Universe Collaboration} and {Audenaert}, Jeroen and {Bowles}, Micah and {Boyd}, Benjamin M. and {Chemaly}, David and {Cherinka}, Brian and {Ciuc{\u{a}}}, Ioana and {Cranmer}, Miles and {Do}, Aaron and {Grayling}, Matthew and {Hayes}, Erin E. and {Hehir}, Tom and {Ho}, Shirley and {Huertas-Company}, Marc and {Iyer}, Kartheik G. and {Jablonska}, Maja and {Lanusse}, Francois and {Leung}, Henry W. and {Mandel}, Kaisey and {Mart{\'\i}nez-Galarza}, Juan Rafael and {Melchior}, Peter and {Meyer}, Lucas and {Parker}, Liam H. and {Qu}, Helen and {Shen}, Jeff and {Smith}, Michael J. and {Stone}, Connor and {Walmsley}, Mike and {Wu}, John F.},
     doi = {10.48550/arXiv.2412.02527},
     eid = {arXiv:2412.02527},
     eprint = {2412.02527},
     journal = {arXiv e-prints},
     keywords = {Astrophysics - Instrumentation and Methods for Astrophysics, Astrophysics - Astrophysics of Galaxies, Astrophysics - Solar and Stellar Astrophysics},
     month = dec,
     pages = {arXiv:2412.02527},
     primaryclass = {astro-ph.IM},
     title = {{The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data}},
     year = {2024}
   }

2. 

   Probabilistic mass-mapping with neural score estimation

   B. Remy, F. Lanusse, N. Jeffrey, and 4 more authors

   Astronomy and Astrophysics Apr 2023

   Abs arXiv Bib Code

   Context. Weak lensing mass-mapping is a useful tool for accessing the full distribution of dark matter on the sky, but because of intrinsic galaxy ellipticies, finite fields, and missing data, the recovery of dark matter maps constitutes a challenging, ill- posed inverse problem \Aims: We introduce a novel methodology that enables the efficient sampling of the high- dimensional Bayesian posterior of the weak lensing mass-mapping problem, relying on simulations to define a fully non-Gaussian prior. We aim to demonstrate the accuracy of the method to simulated fields, and then proceed to apply it to the mass reconstruction of the HST/ACS COSMOS field. \Methods: The proposed methodology combines elements of Bayesian statistics, analytic theory, and a recent class of deep generative models based on neural score matching. This approach allows us to make full use of analytic cosmological theory to constrain the 2pt statistics of the solution, to understand any differences between this analytic prior and full simulations from cosmological simulations, and to obtain samples from the full Bayesian posterior of the problem for robust uncertainty quantification. \Results: We demonstrate the method in the \ensuremathκTNG simulations and find that the posterior mean significantly outperfoms previous methods (Kaiser-Squires, Wiener filter, Sparsity priors) both for the root-mean-square error and in terms of the Pearson correlation. We further illustrate the interpretability of the recovered posterior by establishing a close correlation between posterior convergence values and the S/N of the clusters artificially introduced into a field. Finally, we apply the method to the reconstruction of the HST/ACS COSMOS field, which yields the highest-quality convergence map of this field to date. \Conclusions: We find the proposed approach to be superior to previous algorithms, scalable, providing uncertainties, and using a fully non-Gaussian prior. \\textbackslashAll codes and data products associated with this paper are available at https://github.com/CosmoStat/jax-lensing.

   @article{2023A&A...672A..51R,
     adsnote = {Provided by the SAO/NASA Astrophysics Data System},
     adsurl = {https://ui.adsabs.harvard.edu/abs/2023A&A...672A..51R},
     archiveprefix = {arXiv},
     author = {{Remy}, B. and {Lanusse}, F. and {Jeffrey}, N. and {Liu}, J. and {Starck}, J. -L. and {Osato}, K. and {Schrabback}, T.},
     doi = {10.1051/0004-6361/202243054},
     eid = {A51},
     eprint = {2201.05561},
     journal = {Astronomy and Astrophysics},
     keywords = {cosmology: observations, methods: statistical, gravitational lensing: weak, Astrophysics - Cosmology and Nongalactic Astrophysics, Astrophysics - Instrumentation and Methods for Astrophysics, Computer Science - Machine Learning},
     month = apr,
     pages = {A51},
     primaryclass = {astro-ph.CO},
     title = {{Probabilistic mass-mapping with neural score estimation}},
     volume = {672},
     year = {2023}
   }

3. 

   The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys

   M. Huertas-Company, and F. Lanusse

   Publications of the Astron. Soc. of Australia Jan 2023

   Abs arXiv Bib Website

   The amount and complexity of data delivered by modern galaxy surveys has been steadily increasing over the past years. New facilities will soon provide imaging and spectra of hundreds of millions of galaxies. Extracting coherent scientific information from these large and multi-modal data sets remains an open issue for the community and data-driven approaches such as deep learning have rapidly emerged as a potentially powerful solution to some long lasting challenges. This enthusiasm is reflected in an unprecedented exponential growth of publications using neural networks, which have gone from a handful of works in 2015 to an average of one paper per week in 2021 in the area of galaxy surveys. Half a decade after the first published work in astronomy mentioning deep learning, and shortly before new big data sets such as Euclid and LSST start becoming available, we believe it is timely to review what has been the real impact of this new technology in the field and its potential to solve key challenges raised by the size and complexity of the new datasets. The purpose of this review is thus two-fold. We first aim at summarising, in a common document, the main applications of deep learning for galaxy surveys that have emerged so far. We then extract the major achievements and lessons learned and highlight key open questions and limitations, which in our opinion, will require particular attention in the coming years. Overall, state-of-the-art deep learning methods are rapidly adopted by the astronomical community, reflecting a democratisation of these methods. This review shows that the majority of works using deep learning up to date are oriented to computer vision tasks (e.g. classification, segmentation). This is also the domain of application where deep learning has brought the most important breakthroughs so far. However, we also report that the applications are becoming more diverse and deep learning is used for estimating galaxy properties, identifying outliers or constraining the cosmological model. Most of these works remain at the exploratory level though which could partially explain the limited impact in terms of citations. Some common challenges will most likely need to be addressed before moving to the next phase of massive deployment of deep learning in the processing of future surveys; for example, uncertainty quantification, interpretability, data labelling and domain shift issues from training with simulations, which constitutes a common practice in astronomy.

   @article{2023PASA...40....1H,
     adsnote = {Provided by the SAO/NASA Astrophysics Data System},
     adsurl = {https://ui.adsabs.harvard.edu/abs/2023PASA...40....1H},
     archiveprefix = {arXiv},
     author = {{Huertas-Company}, M. and {Lanusse}, F.},
     doi = {10.1017/pasa.2022.55},
     eid = {e001},
     eprint = {2210.01813},
     journal = {Publications of the Astron. Soc. of Australia},
     keywords = {methods: data analysis, cosmology: observations, cosmology: theory, galaxies: evolution, galaxies: formation, Astrophysics - Instrumentation and Methods for Astrophysics, Astrophysics - Cosmology and Nongalactic Astrophysics, Astrophysics - Astrophysics of Galaxies},
     month = jan,
     pages = {e001},
     primaryclass = {astro-ph.IM},
     title = {{The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys}},
     volume = {40},
     year = {2023}
   }

4. Nat. Rev. Phys

   Bayesian uncertainty quantification for machine-learned models in physics

   Yarin Gal, Petros Koumoutsakos, Francois Lanusse, and 2 more authors

   Nature Reviews Physics Sep 2022

   Abs Bib

   Being able to quantify uncertainty when comparing a theoretical or computational model to observations is critical to conducting a sound scientific investigation. With the rise of data-driven modelling, understanding various sources of uncertainty and developing methods to estimate them has gained renewed attention. Five researchers discuss uncertainty quantification in machine-learned models with an emphasis on issues relevant to physics problems.

   @article{2022NatRP...4..573G,
     adsnote = {Provided by the SAO/NASA Astrophysics Data System},
     adsurl = {https://ui.adsabs.harvard.edu/abs/2022NatRP...4..573G},
     author = {{Gal}, Yarin and {Koumoutsakos}, Petros and {Lanusse}, Francois and {Louppe}, Gilles and {Papadimitriou}, Costas},
     doi = {10.1038/s42254-022-00498-4},
     journal = {Nature Reviews Physics},
     month = sep,
     number = {9},
     pages = {573-577},
     title = {{Bayesian uncertainty quantification for machine-learned models in physics}},
     volume = {4},
     year = {2022}
   }

5. Neural Posterior Estimation with Differentiable Simulator

   Justine Zeghal, Francois Lanusse, Alexandre Boucaud, and 2 more authors

   In Machine Learning for Astrophysics Jul 2022

   Abs arXiv Bib Slides

   Simulation-Based Inference (SBI) is a promising Bayesian inference framework that alleviates the need for analytic likelihoods to estimate posterior distributions. Recent advances using neural density estimators in SBI algorithms have demonstrated the ability to achieve high-fidelity posteriors, at the expense of a large number of simulations ; which makes their application potentially very time-consuming when using complex physical simulations. In this work we focus on boosting the sample- efficiency of posterior density estimation using the gradients of the simulator. We present a new method to perform Neural Posterior Estimation (NPE) with a differentiable simulator. We demonstrate how gradient information helps constrain the shape of the posterior and improves sample-efficiency.

   @inproceedings{2022mla..confE..52Z,
     adsnote = {Provided by the SAO/NASA Astrophysics Data System},
     adsurl = {https://ui.adsabs.harvard.edu/abs/2022mla..confE..52Z},
     archiveprefix = {arXiv},
     author = {{Zeghal}, Justine and {Lanusse}, Francois and {Boucaud}, Alexandre and {Remy}, Benjamin and {Aubourg}, Eric},
     booktitle = {Machine Learning for Astrophysics},
     doi = {10.48550/arXiv.2207.05636},
     eid = {52},
     eprint = {2207.05636},
     keywords = {Astrophysics - Instrumentation and Methods for Astrophysics, Statistics - Machine Learning},
     month = jul,
     pages = {52},
     primaryclass = {astro-ph.IM},
     title = {{Neural Posterior Estimation with Differentiable Simulator}},
     year = {2022}
   }