Bruno Régaldo-Saint Blancard, Ph.D.

I am a Research Fellow in the Center for Computational Mathematics at the Flatiron Institute, New York. I develop statistical methods for astrophysics, cosmology, and beyond using signal processing and machine learning. I am interested in various problems including generative modeling, inference, denoising, and source separation. Lately, I've been particularly focused on deep generative models and how they can be applied to scientific endeavors.

I obtained a Ph.D. in Astrophysics in 2021 from the École Normale Supérieure, Paris. There, I was working on the statistical modeling of the polarized emission of interstellar dust with scattering-like statistics (wavelet scattering transform and phase harmonics). I keep working on data-driven approaches for the modeling of interstellar dust, but also, more recently, on how similar approaches can apply to the statistical analysis of galaxy surveys (within the SimBIG collaboration). I am also part of the Polymathic AI initiative, which aims to create a foundation model for advancing scientific discovery.

Download my CV.
Download my Ph.D. Thesis.

Research Highlights

Removing Dust from CMB Observations with Diffusion Models
October 2023

Diffusion models have revolutionized the modeling of natural images. Can they also help us to analyze CMB data? Thanks to our talented intern David Heurtel-Depeiges, and the collaboration of Blaskeley Burkhart and Ruben Ohana, we make a first demonstration of the potential of diffusion models for the separation of Galactic dust and CMB. We show that dust+CMB observations can be seen as the result of a diffusion process that can be reversed in time, thus naturally solving source separation.

We are already working on the next step: a diffusion-based approach for cosmological inference. Stay tuned!

Stacking for Simulation-Based Inference
October 2023

With simulation-based inference, it is typical to end up with a multitude of models/approximations of the same target posterior distribution. This usually results from the investigation of different inference algorithms, different architectures, or can simply be due to the randomness of initialization and stochastic gradients. While most practitioners usually choose to select the best of their models, with Yuling Yao and Justin Domke, we show that there is much better to do, and it's called stacking. We show that models can all be combined at once in a systematic way to improve precision, calibration, coverage, and bias at the same time. Check out our new preprint on Simulation-Based Stacking!

SimBIG Collaboration: Second Wave of Papers
October 2023

We are taking simulation-based inference for the analysis of galaxy clustering to the next level with our second release of papers! We now explore galaxy clustering data through the lenses of the wavelet scattering transform, convolutional networks, and bispectrum statistics. For each of these, we get new cosmological constraints leveraging non-linear information from the data. Check out our new website for more information!

With Michael Eickenberg, we led the wavelet scattering transform (WST) analysis. The WST statistics capture a wealth of non-Gaussian information from the data improving constraints on cosmological parameters. However, we show in our paper that these statistics might work too well as they can also capture unrealistic specifics of the forward models, raising model misspecifications issues when applied to observational data. Our next challenge will be to address this in detail!

Polymathic AI and Multiple Physics Pretraining
October 2023

I am lucky to be part of the amazing Polymathic AI initiative which aims to create a foundation model for advancing scientific discovery. We recently released a series of paper, check out our blog to find out about it!

In particular, in a project led by Michael McCabe, we introduce “Multiple Physics Pretraining”, an autoregressive task-agnostic pretraining approach for physical surrogate modeling. In this paper, we notably show that a single transformer model trained on a broad range of physical tasks can perform better than task-specific models on a variety of downstream applications.

Statistical Component Separation for Targeted Signal Recovery in Noisy Mixtures
June 2023

In a 2021 paper, we had introduced a new algorithm to separate astrophysical signals with very distinctive statistical natures. Since then, this method has found interest in various astrophysical applications such as the denoising of dust emission maps, the separation of dust and CIB, or the removal of glitches in seismic data from the InSight Mars mission. With Michael Eickenberg, we now explore some mathematical aspects of this method and provide first denoising benchmarks in our new preprint.

SimBIG: Simulation-Based Inference of Galaxies
November 2022

Glad to announce the release of the two first papers of the SimBIG collaboration (led by ChangHoon Hahn): letter, mock challenge. The SimBIG framework enables the analysis of cosmological information from galaxy surveys on small nonlinear scales using simulation-based inference. It relies on the SimBIG forward model, which connects the cosmological parameters to realistic mock galaxy surveys. Take a look at how this model compares to BOSS data!

Generative Models of Multi-frequency Dust Emission Maps
August 2022

Check out our recent paper, where we use the Wavelet Phase Harmonic statistics to build generative models of multi-frequency dust emission maps from a single example. Want to try this on your own data? Take a look at the code associated with the paper.

Wavelet Moments for Cosmological Parameter Estimation
April 2022

I was recently involved in Eickenberg et al. paper, which introduced a new set of wavelet statistics, called "Wavelet Moments", to extract non-Gaussian information from 3D cosmological fields. Fisher forecasts based on the Quijote simulations show that these statistics improve constraints on the cosmological parameters by a factor 5 to 10 with respect to the power spectrum baseline.

Selected Papers

  1. D. Heurtel-Depeiges, B. Burkhart, R. Ohana & B. Régaldo-Saint Blancard; “Removing Dust from CMB Observations with Diffusion Models”; ArXiv
  2. Y. Yao, B. Régaldo-Saint Blancard & J. Domke; “Simulation Based Stacking”; ArXiv
  3. B. Régaldo-Saint Blancard, C. Hahn, S. Ho, J. Hou, P. Lemos, E. Massara, C. Modi, A. Moradinezhad Dizgah, L. Parker, Y. Yao & M. Eickenberg; “SimBIG: Galaxy Clustering Analysis with the Wavelet Scattering Transform”; ArXiv
  4. C. Hahn, P. Lemos, L. Parker, B. Régaldo-Saint Blancard, M. Eickenberg, S. Ho, J. Hou, E. Massara, C. Modi, A. Moradinezhad Dizgah & D. Spergel; “SimBIG: The First Cosmological Constraints from Non-Gaussian and Non-Linear Galaxy Clustering”; ArXiv
  5. M. McCabe, B. Régaldo-Saint Blancard, L. Holden Parker, R. Ohana, M. Cranmer, A. Bietti, M. Eickenberg, S. Golkar, G. Krawezik, F. Lanusse, M. Pettee, T. Tesileanu, K. Cho & S. Ho; “Multiple Physics Pretraining for Physical Surrogate Models”; ArXiv
  6. B. Régaldo-Saint Blancard & M. Eickenberg; “Statistical Component Separation for Targeted Signal Recovery in Noisy Mixtures”; ArXiv
  7. C. Hahn, M. Eickenberg, S. Ho, J. Hou, P. Lemos, E. Massara, C. Modi, A. Moradinezhad Dizgah, B. Régaldo-Saint Blancard & M. Abidi; “SimBIG: A Forward Modeling Approach To Analyzing Galaxy Clustering”; PNAS 120 (42) e2218810120 (2023). ArXivDOI
  8. C. Hahn, M. Eickenberg, S. Ho, J. Hou, P. Lemos, E. Massara, C. Modi, A. Moradinezhad Dizgah, B. Régaldo-Saint Blancard & M. Abidi; “SimBIG: Mock Challenge for a Forward Modeling Approach to Galaxy Clustering”; JCAP 04 (2023) 010. ArXivDOI
  9. B. Régaldo-Saint Blancard, E. Allys, C. Auclair, F. Boulanger, M. Eickenberg, F. Levrier, L. Vacher & S. Zhang; “Generative Models of Multi-channel Data from a Single Example - Application to Dust Emission”; ApJ 943, 9 (2023). ArXivDOI
  10. M. Eickenberg, E. Allys, A. Moradinezhad Dizgah, P. Lemos, E. Massara, M. Abidi, C. Hahn, S. Hassan, B. Régaldo-Saint Blancard, S. Ho, S. Mallat, J. Anden & F. Villaescusa-Navarro; “Wavelet Moments for Cosmological Parameter Estimation”; ArXiv
  11. N. Jeffrey, F. Boulanger, B. D. Wandelt, B. Regaldo-Saint Blancard, E. Allys & F. Levrier; “Single frequency CMB B-mode inference with realistic foregrounds from a single training image”; Monthly Notices of the Royal Astronomical Society: Letters (2021). ArXiv DOI
  12. B. Regaldo-Saint Blancard, E. Allys, F. Boulanger, F. Levrier & N. Jeffrey; “A new approach for the statistical denoising of Planck interstellar dust polarization data”; Astronomy & Astrophysics 649, L18 (2021). ArXiv DOI
  13. B. Regaldo-Saint Blancard, S. Codis, J. R. Bond & G. Stein; “Statistical exploration of halo anisotropic clustering and intrinsic alignments with the mass-Peak Patch algorithm”; Monthly Notices of the Royal Astronomical Society 504, 2, 1694-1713 (2021). ArXiv DOI
  14. B. Regaldo-Saint Blancard, F. Levrier, E. Allys, E. Bellomi & F. Boulanger; “Statistical description of dust polarized emission from the diffuse interstellar medium - A RWST approach”; Astronomy & Astrophysics 642, A217 (2020). ArXiv DOI
  15. E. Allys, F. Levrier, S. Zhang, C. Colling, B. Regaldo-Saint Blancard, F. Boulanger, P. Hennebelle & S. Mallat; “The RWST, a comprehensive statistical description of the non-Gaussian structures in the ISM”; Astronomy & Astrophysics 629, A115 (2019). ArXiv DOI


A list of softwares, all available on my GitHub.

Name Description
PyWST Python package for the statistical analysis of 2D data with the Wavelet Scattering Transform (WST) and the Reduced Wavelet Scattering Transform (RWST).
PyWPH Python package for GPU-accelerated computations of the Wavelet Phase Harmonic (WPH) statistics from 2D data.


I kept track of some of my past talks in my CV. Some of them (rather old ones..) have been recorded, so here are the links:
  • 2019 - Gotham City Physics X ML talk, "Statistical description of the polarized interstellar medium", Flatiron Institute, New-York.
  • 2019 - TEDx talk, "Un Univers sans limite ?", Pôle Universitaire Léonard de Vinci, Paris-La Défense. For French speakers, unless of course you are willing to trust the automatic subtitles of YouTube!