Yashar Hezaveh

Biographie

Yashar Hezaveh est membre associé de Mila – Institut québécois d'intelligence artificielle et directeur de Ciela – Institut de Montréal pour l'analyse des données astrophysiques et l'apprentissage automatique. Il est professeur adjoint au Département de physique de l'Université de Montréal, titulaire d'une chaire de recherche du Canada en analyse de données astrophysiques et apprentissage automatique, membre associé de l'Institut spatial Trottier de l'Université McGill et chercheur invité au Center for Computational Astrophysics du Flatiron Institute (New York) et au Perimeter Institute. Auparavant, il a été chercheur au Flatiron Institute (2018-2019) et boursier Hubble de la NASA à l'Université de Stanford (2013-2018).

Il est un leader mondial dans l'analyse des données astrophysiques avec l'apprentissage automatique. Ses recherches actuelles portent principalement sur l'inférence bayésienne dans l'IA (par exemple, les modèles de diffusion) et visent à faire progresser les connaissances sur la distribution de la matière noire dans les galaxies fortement lenticulaires à l'aide de données provenant de grands relevés cosmologiques. Ses recherches sont soutenues par la Schmidt Futures Foundation et la Simons Foundation.

Étudiants actuels

Missael Barco

Doctorat - UdeM

Superviseur⋅e principal⋅e :

missael-gabriel.barco@mila.quebec

Misha Barth

Doctorat - UdeM

Co-superviseur⋅e :

michael.barth@mila.quebec

Noé Dia

Stagiaire de recherche - UdeM

Superviseur⋅e principal⋅e :

noe.dia@mila.quebec

Dhvani Doshi

Maîtrise recherche - McGill

dhvani.doshi@mila.quebec

Andreas Filipp

Doctorat - UdeM

Superviseur⋅e principal⋅e :

andreas.filipp@umontreal.ca

Doctorat - UdeM

Co-superviseur⋅e :

ronan.legin@mila.quebec

Pablo Lemos

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

parker.levesque@mila.quebec

pablo.lemos@mila.quebec

Maîtrise recherche - UdeM

Co-superviseur⋅e :

Pierre-Luc Bacon

Nicolas Payot

Maîtrise recherche - UdeM

Co-superviseur⋅e :

nicolas.payot@mila.quebec

Sacha Perry-Fagant

Doctorat - UdeM

Superviseur⋅e principal⋅e :

sacha.perry-fagant@mila.quebec

Postdoctorat - UdeM

Co-superviseur⋅e :

nolan.smyth@mila.quebec

Maîtrise recherche - McGill

zach.sumners@mila.quebec

Yitian Sun

Postdoctorat - McGill

Superviseur⋅e principal⋅e :

yitian.sun@mila.quebec

wassim.tenachi@mila.quebec

Wassim Tenachi

Postdoctorat - UdeM

Co-superviseur⋅e :

Pierre-Luc Bacon

Justine Zeghal

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

justine.zeghal@mila.quebec

Publications

Microlensing Detection and Inference via Learned Bayes Factors

We present a unified framework for gravitational microlensing event detection and parameter inference. Traditional pipelines use determinist… (voir plus)ic hard cuts on photometric statistics, systematically missing low-magnification events in the finite-source regime. We instead frame detection as Bayesian model comparison using Evidence Networks, which learn calibrated Bayes factors from binary-labeled simulations, and combine this with Neural Posterior Estimation (NPE) for amortized parameter inference. Both share a transformer encoder that handles irregularly-sampled time series without imputation. On simulated Roman Space Telescope data, our Evidence Network achieves

2026-05-29

AI4Physics @ International Conference on Machine Learning (publié)

openreview.net

Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines

Guillaume Payeur

Gabriel Missael Barco

Modeling galaxy-galaxy strong gravitational lenses to infer the brightness of the source galaxy and the mass distribution of the foreground … (voir plus)galaxy is computationally challenging, particularly for high-resolution, high signal-to-noise observations. In this regime, high-dimensional representations of both the source and the foreground mass distribution are necessary to model the data down to the noise level. This inference problem has been challenging for both traditional and machine learning-based methods because of its high dimensionality and its non-linearity in the foreground mass distribution. We present a method to generate joint posterior samples of the source galaxy and foreground mass distribution as pixelated images conditioned on observations. The method combines diffusion-based generative modeling and recurrent inference machines. It can model realistic gravitational lensing simulations with background and foreground galaxies drawn from cosmological hydrodynamical simulations down to the noise level.

2026-05-29

AI4Physics @ International Conference on Machine Learning (publié)

openreview.net

LSST Strong Lensing Systems Dark Matter Sensitivity Analysis with Neural Ratio Estimators

Andreas Filipp

Daniel Gilman

LSST Dark Energy Science Collaboration

Strong gravitational lensing offers a unique probe of dark matter (DM) on sub-galactic scales, where the abundance and distribution of low-m… (voir plus)ass halos are highly sensitive to the underlying properties of DM particles. In this work, we forecast LSST's sensitivity to DM substructure in galaxy-galaxy strong lenses using simulated samples and neural ratio estimators (NREs). Our simulations include both subhalos within the main deflector and line-of-sight (LOS) halos, with halo masses down to

2026-04-07

arXiv (prépublication)

MIRA: A Score for Conditional Distribution Accuracy and Model Comparison

Sammy Sharief

Justine Zeghal

Gabriel Missael Barco

Pablo Lemos

We present Mira, a method for estimating the expected probability that samples from a candidate conditional distribution match the true, unk… (voir plus)nown conditional distribution, for which only data-label pairs are available. We derive theoretical bounds obtained when the candidate distribution matches the true one and when the conditional distributions are independent. This framework thus enables model comparison by quantifying the alignment between the conditional distribution of a candidate model and the data-label pairs of the true model. Consequently, Mira enables Bayesian model comparison through direct posterior validation, bypassing the challenging evidence computation. We demonstrate its effectiveness across several toy problems and Bayesian inference tasks.

2025-12-31

International Conference on Machine Learning (Accept (spotlight))

openreview.net

Transformer Embeddings for Fast Microlensing Inference

2025-12-11

ArXiv (prépublication)

Neural Deprojection of Galaxy Stellar Mass Profiles

M. J. Yantovski-Barth

Hengyue Zhang

Martin Bureau

We introduce a neural approach to dynamical modeling of galaxies that replaces traditional imaging-based deprojections with a differentiable… (voir plus) mapping. Specifically, we train a neural network to translate Nuker profile parameters into analytically deprojectable Multi Gaussian Expansion components, enabling physically realistic stellar mass models without requiring optical observations. We integrate this model into SuperMAGE, a differentiable dynamical modelling pipeline for Bayesian inference of supermassive black hole masses. Applied to ALMA data, our approach finds results consistent with state-of-the-art models while extending applicability to dust-obscured and active galaxies where optical data analysis is challenging.

2025-11-24

arXiv (prépublication)

Mind the Information Gap: Unveiling Detailed Morphologies of z 0.5-1.0 Galaxies with SLACS Strong Lenses and Data-Driven Analysis

Alexandre Adam

Gabriel Missael Barco

Adam Coogan

Nikolay Malkin

2025-11-23

ArXiv (prépublication)

Pixellated Posterior Sampling of Point Spread Functions in Astronomical Images

Alexandre Adam

Nikolay Malkin

Gabriel Missael Barco

We introduce a novel framework for upsampled Point Spread Function (PSF) modeling using pixel-level Bayesian inference. Accurate PSF charact… (voir plus)erization is critical for precision measurements in many fields including: weak lensing, astrometry, and photometry. Our method defines the posterior distribution of the pixelized PSF model through the combination of an analytic Gaussian likelihood and a highly expressive generative diffusion model prior, trained on a library of HST ePSF templates. Compared to traditional methods (parametric Moffat, ePSF template-based, and regularized likelihood), we demonstrate that our PSF models achieve orders of magnitude higher likelihood and residuals consistent with noise, all while remaining visually realistic. Further, the method applies even for faint and heavily masked point sources, merely producing a broader posterior. By recovering a realistic, pixel-level posterior distribution, our technique enables the first meaningful propagation of detailed PSF morphological uncertainty in downstream analysis. An implementation of our posterior sampling procedure is available on GitHub.

2025-11-23

ArXiv (prépublication)

Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Models

Gabriel Missael Barco

2025-11-05

ArXiv (prépublication)

Bridging Simulators with Conditional Optimal Transport

Justine Zeghal

Benjamin Remy

François Lanusse

2025-10-27

ArXiv (prépublication)

Predicting the Subhalo Mass Functions in Simulations from Galaxy Images

Andreas Filipp

Tri Nguyen

J. Rose

Chris Lovell

Nicolas Payot

Francisco Villaescusa-navarro

2025-10-15

ArXiv (prépublication)

The Interpolation Constraint in the RV Analysis of M-Dwarfs Using Empirical Templates

Dhvani Doshi

Nicolas B. Cowan

E. Artigau

René Doyon

André M. Silva

Khaled Al Moulla

Precise radial velocity (pRV) measurements of M-dwarfs in the near-infrared (NIR) rely on empirical templates due to the lack of accurate st… (voir plus)ellar spectral models in this regime. Templates are assumed to approximate the true spectrum when constructed from many observations or in the high signal-to-noise limit. We develop a numerical simulation that generates SPIRou-like pRV observations from PHOENIX spectra, constructs empirical templates, and estimates radial velocities. This simulation solely considers photon noise and evaluates when empirical templates remain reliable for pRV analysis. Our results reveal a previously unrecognized noise source in templates, establishing a fundamental floor for template-based pRV measurements. We find that templates inherently include distortions in stellar line shapes due to imperfect interpolation at the detector's sampling resolution. The magnitude of this interpolation error depends on sampling resolution and RV content. Consequently, while stars with a higher RV content, such as cooler M-dwarfs are expected to yield lower RV uncertainties, their dense spectral features can amplify interpolation errors, potentially biasing RV estimates. For a typical M4V star, SPIRou's spectral and sampling resolution imposes an RV uncertainty floor of 0.5-0.8 m/s, independent of the star's magnitude or the telescope's aperture. These findings reveal a limitation of template-based pRV methods, underscoring the need for improved spectral modeling and better-than-Nyquist detector sampling to reach the next level of RV precision.

2025-10-14

The Astronomical Journal (publié)