Name: Deep CosmoStat Days
Start: 2026-02-12T09:00:00+01:00
End: 2026-02-14T00:00:00+01:00
Location: CEA/DAp

Deep CosmoStat Days

de jeudi 12 février 2026 (09:00) à samedi 14 février 2026 (00:00)

lundi 9 février 2026
mardi 10 février 2026
mercredi 11 février 2026
jeudi 12 février 2026

09:20 Welcome & Coffee
Welcome & Coffee
09:20 - 09:40
Room: Cassini
09:40 Introduction - Jean-Luc Starck (CosmoStat, CEA Paris-Saclay)
Introduction
- Jean-Luc Starck (CosmoStat, CEA Paris-Saclay)
09:40 - 09:50
Room: Cassini
09:50 Modelling Uncertainty in Multi-Source Data Fusion - Grigorios Tsagkatakis (FORTH)
Modelling Uncertainty in Multi-Source Data Fusion
- Grigorios Tsagkatakis (FORTH)
09:50 - 10:20
Room: Cassini
10:20 On Diffusion Models for Inverse Problems - François LANUSSE (AIM, CNRS/CEA Paris-Saclay)
On Diffusion Models for Inverse Problems
- François LANUSSE (AIM, CNRS/CEA Paris-Saclay)
10:20 - 10:50
Room: Cassini Diffusion models are emerging as powerful tools for probabilistic prediction and inference in the physical sciences, but their application faces key challenges: high-dimensional state spaces, partial observability, and expensive simulations. In this talk, I present a unified diffusion-based framework addressing these issues across three complementary directions. First, latent-space diffusion models enable fast, high-fidelity emulation of complex dynamical systems at a fraction of the computational cost. Second, we introduce an expectation-maximization approach that learns diffusion priors directly from incomplete and noisy observations, enabling principled Bayesian inference without fully observed training data. Third, we embed diffusion models into a multiscale temporal inference scheme that improves stability and accuracy in partially observable systems. Together, these methods demonstrate how diffusion models can serve as scalable, uncertainty-aware engines for physical prediction and inference. https://arxiv.org/abs/2507.02608 https://arxiv.org/abs/2511.19390 https://arxiv.org/abs/2405.13712
10:50 CHEM- Estimating and Understanding Hallucinations in Deep Learning for Image Processing - Ines Rosellon Inclan (LMU)
CHEM- Estimating and Understanding Hallucinations in Deep Learning for Image Processing
- Ines Rosellon Inclan (LMU)
10:50 - 11:10
Room: Cassini U-Net and other U-shaped architectures have become standard tools for image deconvolution in astronomy and related imaging tasks. Despite their success, these models might produce unrealistic artifacts, or hallucinations, which can compromise analysis in safety-critical settings. In this talk, I will present CHEM (Conformal Hallucination Estimation Metric), a general framework for identifying and quantifying hallucination artifacts in deep learning–based image reconstruction models. CHEM is model-agnostic and combines multiscale wavelet and shearlet representations with conformalized quantile regression to assess hallucination levels in a distribution-free manner. I will focus in particular on experimental results obtained on the CANDELS dataset, comparing different architectures such as U-Net, Swin-UNet, and Learnlets. These results provide new insights into how hallucinations manifest across models and scales, and how they can be systematically detected and analyzed in practice.
11:10 Learnlets on the sphere - Victor Bonjean (FORTH)
Learnlets on the sphere
- Victor Bonjean (FORTH)
11:10 - 11:30
Room: Cassini
11:30 A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping - Hubert Leterme (CEA IRFU/DAp)
A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping
- Hubert Leterme (CEA IRFU/DAp)
11:30 - 11:50
Room: Cassini Stage-IV surveys such as Euclid will deliver vast amounts of high-precision data, opening new opportunities to constrain cosmological models with unprecedented accuracy. A key step in this process is the reconstruction of the dark matter distribution from noisy weak lensing shear measurements. Current deep learning-based mass mapping methods achieve high accuracy, but either require retraining a model for each new observed sky region (limiting practicality) or rely on slow MCMC sampling. Efficient exploitation of future survey data therefore calls for a new method that is accurate, flexible, and fast at inference. In addition, uncertainty quantification with coverage guarantees is essential for reliable cosmological parameter estimation. In this talk, we introduce PnPMass, a plug-and-play approach for weak lensing mass mapping. The algorithm produces point estimates by alternating between a gradient descent step with a carefully chosen data fidelity term, and a denoising step implemented with a single deep learning model trained on simulated data corrupted by Gaussian white noise. We also propose a fast, sampling-free uncertainty quantification scheme based on moment networks, with calibrated error bars obtained through conformal prediction to ensure coverage guarantees. Finally, we benchmark PnPMass against both model-driven and data-driven mass mapping techniques. PnPMass achieves performance close to that of state-of-the-art deep-learning methods while offering fast inference (converging in just a few iterations) and requiring only a single training phase, independently of the noise covariance of the observations. It therefore combines flexibility, efficiency, and accuracy, while delivering tighter error bars than existing approaches, making it well suited for upcoming stage-IV weak lensing surveys.
14:25 The Hubble Tension in Light of the Symmetry of Scale Invariance - Frederic Courbin (ICCUB - IEEC - ICREA)
The Hubble Tension in Light of the Symmetry of Scale Invariance
- Frederic Courbin (ICCUB - IEEC - ICREA)
14:25 - 14:55
Room: Cassini When the expansion rate of the Universe at recombination is used to infer the present expansion rate 𝐻0, the value derived in the ΛCDM model, 𝐻0 =67.4 km s−1 Mpc−1, is about in 6 𝜎 tension with the value measured locally, 𝐻0 =74 km s−1 Mpc−1. In this work, we consider instead the expansion history in the context of the symmetry of scale-invariant vacuum (SIV model). We first perform two major cosmological tests: the Hubble diagram for type-Ia supernovae and the fundamental relation between 𝐻0, the age of the Universe, and the total density of matter, Ωm. This allows us to constrain Ωm in SIV, with both tests giving the best agreement for Ωm = 0.20. We then study the physical connections of the dynamical and thermal states of the Universe at recombination with the present Hubble constant, 𝐻0, and the present temperature, T, in the ΛCDM and SIV contexts. We find that, in SIV, the properties at recombination may be conveyed to the present ones (𝑇 =2.726 and 𝐻0 at 𝑧 =0) without any tension, indicating 𝐻0 =74 km s−1 Mpc−1 in spite of the anchoring on the CMB. This is due to the slightly different expansion and temperature histories of the two cosmological models. Importantly, this happens to occur for Ωm = 0.20, as constrained in SIV with supernovae and cosmic age. This suggests that the Hubble tension currently found between 𝐻0 values in the early and late Universe may simply be the result of Λ⁢𝐶⁢𝐷⁢𝑀 ignoring the small but still measurable effects of scale invariance.
14:55 Weak lensing
14:55 - 17:10
Room: Cassini
Contributions

14:55 UNIONS cosmological results with 2D weak lensing - Martin KILBINGER (CEA Saclay/Irfu/DAp)

15:25 Inferring 3D shapes and measuring intrinsic alignments of galaxies with UNIONS - Antonin Corinaldi (CEA Paris-Saclay / AIM / CosmoStat)

16:10 Impact of Baryonic Physics on Weak Lensing Statistics - Andreas Tersenov

16:30 Probing large-scale structures through cross-correlations of the tSZ effect - Emma Aycoberry (CosmoStat, CEA Paris-Saclay)

16:50 Convergence map emulator & validation - Vilasini Tinnaneri Sreekanth
17:10 AI Vision for the battlefield: IMINT and Embedded Video Processing - Arnaud Woiselle (Safran)
AI Vision for the battlefield: IMINT and Embedded Video Processing
- Arnaud Woiselle (Safran)
17:10 - 17:40
Room: Cassini
vendredi 13 février 2026
10:00 IA: 1
1
10:00 - 11:10
Room: Cassini
Contributions

10:00 Learning Domain-Invariant Representations via Optimal Transport and Spectral Embeddings - Fred Ngole (CEA/DRT)

10:30 Inferring Physical Properties of High-z Galaxies from IFU Spectral Data cubes: Signal Enhancement and Data-Driven Mapping Beyond Power-Law Relations - Arnab Lahiry (FORTH)

10:50 Uncertainty Quantification for Generative Models in Astrophysics - Sammy Sharief (CEA)
11:10 Break
Break
11:10 - 11:30
Room: Cassini
11:30 Radio Astronomy
11:30 - 12:30
Room: Cassini
Contributions

11:30 Foreground removal in HI 21 cm intensity mapping under frequency-dependent beam distortions - Athanasia Gkogkou (IA/ICS-FORTH)

11:50 Generative model for shear inference in the context of radio weak gravitational lensing - Ezequiel Centofanti (CosmoStat, CEA Paris-Saclay)

12:10 Starlet l1-norm for neutral hydrogen intensity mapping - Pauline Gorbatchev (FORTH)
14:00 Discussions

14:00 - 16:00
Room: Cassini
samedi 14 février 2026

Choisissez le fuseau horaire