Portrait of Yashar Hezaveh

Yashar Hezaveh

Associate Academic Member
Assistant Professor, Université de Montréal, Department of Physics
Research Topics
Computer Vision
Deep Learning
Representation Learning

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

Master's Research - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Master's Research - McGill University
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Postdoctorate - Université de Montréal
Principal supervisor :
Master's Research - Université de Montréal
Co-supervisor :
Master's Research - Université de Montréal
PhD - Université de Montréal
Principal supervisor :
Postdoctorate - Université de Montréal
Postdoctorate - Université de Montréal
Principal supervisor :
Master's Research - McGill University
Postdoctorate - McGill University
Principal supervisor :
Postdoctorate - Université de Montréal
Co-supervisor :
Postdoctorate - Université de Montréal
Principal supervisor :

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
Sarah C. Gallagher
Frederic J. Grandmont
Daryl Haggard
Paul Harrison … (see 160 more)
Vincent Hénault-Brunet
J. Kavelaars
V. Khatu
J. Roediger
J. Rowe
Marcin Sawicki
Jesper Skottfelt
Matt Taylor
Ludo 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
A. Subramaniam
David Thilke
I. Wevers
Dmitri Vorobiev
L. Y. Aaron Yung
Frédéric Zamkotsian
S. Aigrain
A. Alavi
Martin Barstow
Peter Bartosik
Hadleigh Bluhm
J. Bovy
Peter Cameron
R. Carlberg
Jessie L. Christiansen
Yuyang Chen
Paul 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
Morgan Fraser
Boris T. Gaensicke
Shashkiran Ganesh
Poshak Gandhi
Melissa L. Graham
Rebecca Hamel
Martin Hellmich
John J. Hennessy
Kaitlyn Hessel
J. Heyl
Catherine Heymans
Renée Hložek
Michael Hoenk
Andrew Holland
Eric Huff
Ian Hutchinson
Ikuru 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
Sungsoon Lim
Bethany 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
Jade Yeung
S. K. Yi
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
Sarah C. Gallagher
Frederic J. Grandmont
Daryl Haggard
Paul Harrison … (see 160 more)
Vincent Hénault-Brunet
J. Kavelaars
V. Khatu
J. Roediger
J. Rowe
Marcin Sawicki
Jesper Skottfelt
Matt Taylor
Ludo 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
A. Subramaniam
David Thilke
I. Wevers
Dmitri Vorobiev
L. Y. Aaron Yung
Frédéric Zamkotsian
S. Aigrain
A. Alavi
Martin Barstow
Peter Bartosik
Hadleigh Bluhm
J. Bovy
Peter Cameron
R. Carlberg
Jessie L. Christiansen
Yuyang Chen
Paul 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
Morgan Fraser
Boris T. Gaensicke
Shashkiran Ganesh
Poshak Gandhi
Melissa L. Graham
Rebecca Hamel
Martin Hellmich
John J. Hennessy
Kaitlyn Hessel
J. Heyl
Catherine Heymans
Renée Hložek
Michael Hoenk
Andrew Holland
Eric Huff
Ian Hutchinson
Ikuru Iwata
April D. Jewell
Doug Johnstone
Maia Jones
Todd Jones
D. Lang
J. Lapington
Justin Larivière
C. Lawlor-Forsyth
Denis Laurin
Charles Lee
Ronan Legin
Ting S. Li
Sungsoon Lim
Bethany 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
Jade Yeung
Sukyoung K. Yi
The CASTOR mission
Patrick Côté
Tyrone E. Woods
John B. Hutchings
Jason D. Rhodes
Rubén Sánchez-Janssen
Alan D. Scott
John Pazder
Melissa Amenouche
Michael Balogh
Simon Blouin
Alain Cournoyer
Maria R. Drout
Nick Kuzmin
Katherine J. Mack
Laura Ferrarese
Wesley C. Fraser
Sarah C. Gallagher
Frédéric Grandmont
Daryl Haggard
Paul Harrison … (see 160 more)
Vincent Hénault-Brunet
J. J. Kavelaars
Viraja Khatu
Joel C. Roediger
Jason Rowe
Marcin Sawicki
Jesper Skottfelt
Matt Taylor
Ludo van Waerbeke
Laurie Amen
Dhananjhay Bansal
Martin Bergeron
Toby Brown
Greg Burley
Hum Chand
Isaac Cheng
Ryan Cloutier
Nolan Dickson
Oleg Djazovski
Ivana Damjanov
James Doherty
Kyle Finner
Macarena García Del Valle Espinosa
Jennifer Glover
Ana I. Gómez de Castro
Or Graur
Tim Hardy
Michelle Kao
Denis Leahy
Deborah Lokhorst
Alex I. Malz
Allison Man
Madeline A. Marshall
Sean McGee
Ryan McKenzie
Kai Michaud
Surhud S. More
David Morris
Patrick W. Morris
Thibaud Moutard
Wasi Naqvi
Matt Nicholl
Gaël Noirot
M. S. Oey
Cyrielle Opitom
Samir Salim
Bryan R. Scott
Charles A. Shapiro
Daniel Stern
Annapurni Subramaniam
David Thilke
Ivan Wevers
Dmitri Vorobiev
L. Y. Aaron Yung
Frédéric Zamkotsian
Suzanne Aigrain
Anahita Alavi
Martin Barstow
Peter Bartosik
Hadleigh Bluhm
Jo Bovy
Peter Cameron
Raymond G. Carlberg
Jessie L. Christiansen
Yuyang Chen
Paul Crowther
Kristen Dage
Aaron L. Dotter
Patrick Dufour
Jean Dupuis
Ben Dryer
Angaraj Duara
Gwendolyn M. Eadie
Marielle R. Eduardo
Vincente Estrada-Carpenter
Sébastien Fabbro
Andreas Faisst
Nicole M. Ford
Morgan Fraser
Boris T. Gaensicke
Shashkiran Ganesh
Poshak Gandhi
Melissa L. Graham
Rebecca Hamel
Martin Hellmich
John Hennessy
Kaitlyn Hessel
Jeremy Heyl
Catherine Heymans
Renée Hložek
Michael E. Hoenk
Andrew Holland
Eric Huff
Ian Hutchinson
Ikuru Iwata
April D. Jewell
Doug Johnstone
Maia Jones
Todd Jones
Dustin Lang
Jon Lapington
Justin Larivière
Cameron Lawlor-Forsyth
Denis Laurin
Charles Lee
Ronan Legin
Ting S. Li
Sungsoon Lim
Bethany Ludwig
Matt Kozun
Vivek M.
Robert Mann
Alan W. McConnachie
Evan McDonough
Stanimir Metchev
David R. Miller
Takashi Moriya
Cameron Morgan
Julio Navarro
Yaël Nazé
Shouleh Nikzad
Vivek Oad
Nathalie Ouellette
Emily K. Pass
Will J. Percival
Laurence Perreault Levasseur
Joe Postma
Nayyer Raza
Gordon T. Richards
Harvey Richer
Carmelle Robert
Erik Rosolowsky
John J. Ruan
Sarah Rugheimer
Samar Safi-Harb
Kanak Saha
Vicky Scowcroft
Federico Sestito
Himanshu Sharma
James Sikora
Gregory R. Sivakoff
Thirupathi Sivarani
Patrick Smith
Warren Soh
Robert Sorba
Smitha Subramanian
Hossen Teimoorinia
Harry I. Teplitz
Shaylin Thadani
Shavon Thadani
Aaron Tohuvavohu
Kim A. Venn
Nicholas Vieira
Jeremy J. Webb
Paul Wiegert
Ryan Wierckx
Yanqin Wu
Jade Yeung
Sukyoung K. Yi
Echoes in the Noise: Posterior Samples of Faint Galaxy Surface Brightness Profiles with Score-Based Likelihoods and Priors
Alexandre Adam
Connor Stone
Connor Bottrell
Ronan Legin
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 non-trivial noise properties of real astronomical images and the point spread function (PSF) 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 \emph{Hubble Space Telescope} (\emph{HST}) data, recovers structures which have otherwise only become visible in next-generation \emph{James Webb Space Telescope} (\emph{JWST}) imaging.
Solving Bayesian inverse problems with diffusion priors and off-policy RL
Luca Scimeca
Siddarth Venkatraman
Moksh J. Jain
Minsu Kim
Marcin Sendera
Mohsin Hasan
Luke Rowe
Sarthak Mittal
Pablo Lemos
Alexandre Adam
Jarrid Rector-Brooks
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.
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.
A Data-driven Discovery of the Causal Connection between Galaxy and Black Hole Evolution
Zehao Jin
Mario Pasquato
Benjamin L. Davis
Tristan Deleu
Yu Luo
Changhyun Cho
Pablo Lemos
Xi 熙 Kang 康
Andrea Maccio
PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation
Pablo Lemos
Sammy Nasser Sharief
Nikolay Malkin
Salma Salhi
Connor Stone
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.
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.
Robustness of Neural Ratio and Posterior Estimators to Distributional Shifts for Population-Level Dark Matter Analysis in Strong Gravitational Lensing
Beyond Causal Discovery for Astronomy: Learning Meaningful Representations with Independent Component Analysis
Zehao Jin
Mario Pasquato
Benjamin L. Davis
Andrea Maccio