Yashar Hezaveh

Google Scholar

Biography

Yashar Hezaveh is an associate academic member of Mila – Quebec Artificial Intelligence Institute and director of the Montréal Institute for Astrophysical Data Analysis and Machine Learning (Ciela). He is an assistant professor in the Department of Physics at Université de Montréal and the Canada Research Chair in Astrophysical Data Analysis and Machine Learning. In addition, Hezaveh is an associate member of McGill University’s Trottier Space Institute, and a visiting fellow at the Center for Computational Astrophysics at Flatiron Institute in New York and at the Perimeter Institute for Theoretical Physics in Waterloo, Ontario. He was previously a research fellow at the Flatiron Institute (2018–2019) and a NASA Hubble Fellow at Stanford University (2013–2018).

Hezaveh is a world leader in the analysis of astrophysical data using deep learning. His current research focuses primarily on Bayesian inference in AI, the goal being to learn about the distribution of dark matter in strongly lensed galaxies using data from large cosmological surveys. His research is supported by the Schmidt Futures Foundation and the Simons Foundation.

Current Students

Missael Barco

PhD - Université de Montréal

Principal supervisor :

Google Scholar

Misha Barth

PhD - Université de Montréal

Co-supervisor :

Noé Dia

Research Intern - Université de Montréal

Principal supervisor :

Dhvani Doshi

Master's Research - McGill University

Andreas Filipp

PhD - Université de Montréal

Principal supervisor :

Ronan Legin

PhD - Université de Montréal

Co-supervisor :

Pablo Lemos

Postdoctorate - Université de Montréal

Principal supervisor :

Master's Research - Université de Montréal

Co-supervisor :

Pierre-Luc Bacon

Nicolas Payot

Master's Research - Université de Montréal

Co-supervisor :

Sacha Perry-Fagant

PhD - Université de Montréal

Principal supervisor :

Nolan Smyth

Postdoctorate - Université de Montréal

Co-supervisor :

Master's Research - McGill University

Yitian Sun

Postdoctorate - McGill University

Principal supervisor :

Wassim Tenachi

Postdoctorate - Université de Montréal

Co-supervisor :

Postdoctorate - Université de Montréal

Principal supervisor :

Google Scholar

Publications

The CASTOR mission

Patrick Côté

T. Woods

John Hutchings

J. Rhodes

R. Sánchez-Janssen

Alan D. Scott

J. Pazder

Melissa Amenouche

Michael Balogh

Simon Blouin

Alain Cournoyer

M. Drout

Nick Kuzmin

Katherine J. Mack

Laura Ferrarese

Wesley C. Fraser

S. Gallagher

Frederic J. Grandmont

Daryl Haggard

P. Harrison … (see 160 more)

V. Hénault-Brunet

J. Kavelaars

V. Khatu

J. Roediger

J. Rowe

Marcin Sawicki

Jesper Skottfelt

Matt Taylor

L. van Waerbeke

Laurie Amen

Dhananjhay Bansal

Martin Bergeron

Toby Brown

Greg Burley

Hum Chand

Isaac Cheng

Ryan Cloutier

N. Dickson

Oleg Djazovski

Ivana Damjanov

James Doherty

K. Finner

Macarena García Del Valle Espinosa

Jennifer Glover

A. I. Gómez de Castro

Or Graur

Tim Hardy

Michelle Kao

D A Leahy

Deborah Lokhorst

A. I. Malz

Allison Man

Madeline A. Marshall

Sean McGee

Ryan McKenzie

Kai Michaud

Surhud S. More

David Morris

Patrick W. Morris

T. Moutard

Wasi Naqvi

Matthew Nicholl

G. Noirot

M. S. Oey

C. Opitom

Samir Salim

Bryan R. Scott

Charles Shapiro

Daniel Stern

Ashwin Subramaniam

David Thilke

I. Wevers

Dmitri Vorobiev

L. Y. Aaron Yung

Frédéric Zamkotsian

S. Aigrain

A. Alavi

Martin Barstow

Peter Bartosik

H. Bluhm

J. Bovy

Peter Cameron

R. Carlberg

J. Christiansen

Yuyang Chen

P. Crowther

Kristen Dage

Aaron Dotter

Patrick Dufour

Jean Dupuis

B. Dryer

A. Duara

Gwendolyn M. Eadie

Marielle R. Eduardo

V. Estrada-Carpenter

Sébastien Fabbro

A. Faisst

N. M. Ford

M. Fraser

Boris T. Gaensicke

Shashkiran Ganesh

Poshak Gandhi

Melissa L. Graham

R. Hamel

Martin Hellmich

John J. Hennessy

Kaitlyn Hessel

J. Heyl

Catherine Heymans

Renée Hložek

Michael Hoenk

Andrew Holland

Eric Huff

Ian Hutchinson

I. Iwata

April D. Jewell

Doug Johnstone

Maia Jones

Todd J. Jones

D. Lang

J. Lapington

Justin Larivière

C. Lawlor-Forsyth

Denis Laurin

Charles Lee

Ronan Legin

Ting S. Li

S. Lim

B. Ludwig

Matt Kozun

V. M

Robert Mann

Alan McConnachie

Evan McDonough

S. Metchev

David R. Miller

Takashi Moriya

Cameron Morgan

Julio F. Navarro

Y. Nazé

Shouleh Nikzad

Vivek Oad

N. N.-Q. Ouellette

E. Pass

Will J. Percival

Joe Postma

Nayyer Raza

G. T. Richards

Harvey Richer

Carmelle Robert

Erik Rosolowsky

J. Ruan

Sarah Rugheimer

S. Safi-Harb

Kanak Saha

Vicky Scowcroft

F. Sestito

Himanshu Sharma

James Sikora

G. Sivakoff

T. S. Sivarani

Patrick Smith

Warren Soh

R. Sorba

S. Subramanian

Hossen Teimoorinia

H. Teplitz

Shaylin Thadani

Shavon Thadani

Aaron Tohuvavohu

K. Venn

Nicholas Vieira

Jeremy J. Webb

P. Wiegert

Ryan Wierckx

Yanqin Wu

J. Yeung

S. K. Yi

2025-05-13

Journal of Astronomical Telescopes Instruments and Systems (published)

Echoes in the Noise: Posterior Samples of Faint Galaxy Surface Brightness Profiles with Score-based Likelihoods and Priors

Connor Bottrell

Laurence Perreaul-Levasseur

Examining the detailed structure of galaxy populations provides valuable insights into their formation and evolution mechanisms. Significant… (see more) barriers to such analysis are the nontrivial noise properties of real astronomical images and the point-spread function, which blurs structure. Here we present a framework which combines recent advances in score-based likelihood characterization and diffusion model priors to perform a Bayesian analysis of image deconvolution. The method, when applied to minimally processed Hubble Space Telescope data, recovers structures which have otherwise only become visible in next-generation James Webb Space Telescope imaging.

2025-04-07

Astronomical Journal (published)

Solving Bayesian Inverse Problems with Diffusion Priors and Off-Policy RL

Yoshua Bengio

Glen Berseth

Nikolay Malkin

This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (R… (see more)L) objective that can asymptotically solve Bayesian inverse problems optimally. We extend the original work by using RTB to train conditional diffusion model posteriors from pretrained unconditional priors for challenging linear and non-linear inverse problems in vision, and science. We use the objective alongside techniques such as off-policy backtracking exploration to improve training. Importantly, our results show that existing training-free diffusion posterior methods struggle to perform effective posterior inference in latent space due to inherent biases.

2025-03-05

ICLR.cc/2025/Workshop/DeLTa (poster)

Tackling the Problem of Distributional Shifts: Correcting Misspecified, High-Dimensional Data-Driven Priors for Inverse Problems

Gabriel Missael Barco

Alexandre Adam

Connor Stone

Bayesian inference for inverse problems hinges critically on the choice of priors. In the absence of specific prior information, population-… (see more)level distributions can serve as effective priors for parameters of interest. With the advent of machine learning, the use of data-driven population-level distributions (encoded, e.g., in a trained deep neural network) as priors is emerging as an appealing alternative to simple parametric priors in a variety of inverse problems. However, in many astrophysical applications, it is often difficult or even impossible to acquire independent and identically distributed samples from the underlying data-generating process of interest to train these models. In these cases, corrupted data or a surrogate, e.g. a simulator, is often used to produce training samples, meaning that there is a risk of obtaining misspecified priors. This, in turn, can bias the inferred posteriors in ways that are difficult to quantify, which limits the potential applicability of these models in real-world scenarios. In this work, we propose addressing this issue by iteratively updating the population-level distributions by retraining the model with posterior samples from different sets of observations and showcase the potential of this method on the problem of background image reconstruction in strong gravitational lensing when score-based models are used as data-driven priors. We show that starting from a misspecified prior distribution, the updated distribution becomes progressively closer to the underlying population-level distribution, and the resulting posterior samples exhibit reduced bias after several updates.

2025-02-05

The Astrophysical Journal (published)

Causal Discovery in Astrophysics: Unraveling Supermassive Black Hole and Galaxy Coevolution

Zehao Jin

Mario Pasquato

Benjamin L. Davis

Tristan Deleu

Yu Luo

Changhyun Cho

Pablo Lemos

Yoshua Bengio

Xi Kang

Andrea Valerio Maccio

Correlation does not imply causation, but patterns of statistical association between variables can be exploited to infer a causal structure… (see more) (even with purely observational data) with the burgeoning field of causal discovery. As a purely observational science, astrophysics has much to gain by exploiting these new methods. The supermassive black hole (SMBH)--galaxy interaction has long been constrained by observed scaling relations, that is low-scatter correlations between variables such as SMBH mass and the central velocity dispersion of stars in a host galaxy's bulge. This study, using advanced causal discovery techniques and an up-to-date dataset, reveals a causal link between galaxy properties and dynamically-measured SMBH masses. We apply a score-based Bayesian framework to compute the exact conditional probabilities of every causal structure that could possibly describe our galaxy sample. With the exact posterior distribution, we determine the most likely causal structures and notice a probable causal reversal when separating galaxies by morphology. In elliptical galaxies, bulge properties (built from major mergers) tend to influence SMBH growth, while in spiral galaxies, SMBHs are seen to affect host galaxy properties, potentially through feedback in gas-rich environments. For spiral galaxies, SMBHs progressively quench star formation, whereas in elliptical galaxies, quenching is complete, and the causal connection has reversed. Our findings support theoretical models of hierarchical assembly of galaxies and active galactic nuclei feedback regulating galaxy evolution. Our study suggests the potentiality for further exploration of causal links in astrophysical and cosmological scaling relations, as well as any other observational science.

2025-01-27

The Astrophysical Journal (published)

PQMass: Probabilistic Assessment of the Quality of Generative Models Using Probability Mass Estimation

Pablo Lemos

Sammy Sharief

Nikolay Malkin

Salma Salhi

Connor Stone

We propose a likelihood-free method for comparing two distributions given samples from each, with the goal of assessing the quality of gener… (see more)ative models. The proposed approach, PQMass, provides a statistically rigorous method for assessing the performance of a single generative model or the comparison of multiple competing models. PQMass divides the sample space into non-overlapping regions and applies chi-squared tests to the number of data samples that fall within each region, giving a

2025-01-21

International Conference on Learning Representations (poster)

IRIS: A Bayesian Approach for Image Reconstruction in Radio Interferometry with expressive Score-Based priors

No'e Dia

M. J. Yantovski-Barth

Alexandre Adam

Micah Bowles

Anna M. M. Scaife

Inferring sky surface brightness distributions from noisy interferometric data in a principled statistical framework has been a key challeng… (see more)e in radio astronomy. In this work, we introduce Imaging for Radio Interferometry with Score-based models (IRIS). We use score-based models trained on optical images of galaxies as an expressive prior in combination with a Gaussian likelihood in the uv-space to infer images of protoplanetary disks from visibility data of the DSHARP survey conducted by ALMA. We demonstrate the advantages of this framework compared with traditional radio interferometry imaging algorithms, showing that it produces plausible posterior samples despite the use of a misspecified galaxy prior. Through coverage testing on simulations, we empirically evaluate the accuracy of this approach to generate calibrated posterior samples.

2025-01-04

ArXiv (preprint)

Beyond Causal Discovery for Astronomy: Learning Meaningful Representations with Independent Component Analysis

Zehao Jin

Mario Pasquato

Benjamin L. Davis

Andrea Maccio

2024-10-29

NeurIPS.cc/2024/Workshop/CRL (poster)

Improving Gradient-Guided Nested Sampling for Posterior Inference

Will Handley

We present a performant, general-purpose gradient-guided nested sampling algorithm, …

2024-07-07

Proceedings of the 41st International Conference on Machine Learning (published)

proceedings.mlr.press

Neural Ratio Estimators Meet Distributional Shift and Mode Misspecification: A Cautionary Tale from Strong Gravitational Lensing

Andreas Filipp

In recent years, there has been increasing interest in the field of astrophysics in applying Neural Ratio Estimators (NREs) to large-scale i… (see more)nference problems where both amortization and marginalization over a large number of nuisance parameters are needed. Here, in order to assess the true potential of this method to produce unbiased inference on real data, we investigate the robustness of NREs to distribution shifts and model misspecification in the specific scientific application of the measurement of dark matter population-level parameters using strong gravitational lensing. We investigate the behaviour of a trained NRE for test data presenting distributional shifts inside the bounds of training, as well as out of distribution, both in the linear and non-linear parameters of this problem. While our results show that NREs perform when tested perfectly in distribution, we find that they exhibit significant biases and drawbacks when confronted with slight deviations from the examples seen in the training distribution. This indicates the necessity for caution when applying NREs to real astrophysical data, where underlying distributions are not perfectly known and models do not perfectly reconstruct the true underlying distributions.

2024-06-16

ICML.cc/2024/Workshop/SPIGM (poster)