Yashar Hezaveh

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 :

missael-gabriel.barco@mila.quebec

Misha Barth

PhD - Université de Montréal

Co-supervisor :

michael.barth@mila.quebec

Dhvani Doshi

Master's Research - McGill University

dhvani.doshi@mila.quebec

Andreas Filipp

PhD - Université de Montréal

Principal supervisor :

andreas.filipp@umontreal.ca

Ronan Legin

PhD - Université de Montréal

Co-supervisor :

ronan.legin@mila.quebec

Nicolas Payot

Master's Research - Université de Montréal

Co-supervisor :

nicolas.payot@mila.quebec

Sacha Perry-Fagant

PhD - Université de Montréal

Principal supervisor :

sacha.perry-fagant@mila.quebec

Nolan Smyth

Postdoctorate - Université de Montréal

Co-supervisor :

nolan.smyth@mila.quebec

Yitian Sun

Postdoctorate - McGill University

Principal supervisor :

yitian.sun@mila.quebec

wassim.tenachi@mila.quebec

Wassim Tenachi

Postdoctorate - Université de Montréal

Co-supervisor :

Pierre-Luc Bacon

Justine Zeghal

Postdoctorate - Université de Montréal

Principal supervisor :

justine.zeghal@mila.quebec

Publications

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

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

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

Nikolay Malkin

Will Handley

Yoshua Bengio

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

2024-07-22

International Conference on Machine Learning (Accept (Poster))

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)

Inpainting Galaxy Counts onto N-Body Simulations over Multiple Cosmologies and Astrophysics

Matthew Ho

2024-06-15

ICML.cc/2024/Workshop/AI4Science (poster)

Variable Star Light Curves in Koopman Space

Nicolas Mekhaël

Mario Pasquato

GAIA CARENINI

Vittorio F. Braga

PIERO TREVISAN

Giuseppe Bono

2024-06-15

ICML.cc/2024/Workshop/AI4Science (spotlight)

TEMPLATES: Characterization of a Merger in the Dusty Lensing SPT0418-47 System

Jared Cathey

Anthony H. Gonzalez

Sidney Lower

Kedar A. Phadke

Justin Spilker

Manuel Aravena

Matthew Bayliss

Jack E. Birkin

Simon Birrer

Scott Chapman

Hakon Dahle

Christopher C. Hayward

Ryley Hill

Taylor A. Hutchison

Keunho J. Kim

Guillaume Mahler

Daniel P. Marrone

Desika Narayanan

Alexander Navarre … (see 7 more)

Cassie Reuter

Jane R Rigby

Keren Sharon

Manuel Solimano

Nikolaus Sulzenauer

Joaquin Vieira

David Vizgan

2024-05-12

The Astrophysical Journal (published)

On Diffusion Modeling for Anomaly Detection

Known for their impressive performance in generative modeling, diffusion models are attractive candidates for density-based anomaly detectio… (see more)n. This paper investigates different variations of diffusion modeling for unsupervised and semi-supervised anomaly detection. In particular, we find that Denoising Diffusion Probability Models (DDPM) are performant on anomaly detection benchmarks yet computationally expensive. By simplifying DDPM in application to anomaly detection, we are naturally led to an alternative approach called Diffusion Time Estimation (DTE). DTE estimates the distribution over diffusion time for a given input and uses the mode or mean of this distribution as the anomaly score. We derive an analytical form for this density and leverage a deep neural network to improve inference efficiency. Through empirical evaluations on the ADBench benchmark, we demonstrate that all diffusion-based anomaly detection methods perform competitively for both semi-supervised and unsupervised settings. Notably, DTE achieves orders of magnitude faster inference time than DDPM, while outperforming it on this benchmark. These results establish diffusion-based anomaly detection as a scalable alternative to traditional methods and recent deep-learning techniques for standard unsupervised and semi-supervised anomaly detection settings.

2024-05-06

International Conference on Learning Representations (Accept (spotlight))

Interpretable machine learning for finding intermediate-mass black holes

Mario Pasquato

PIERO TREVISAN

ABBAS ASKAR

GAIA CARENINI

MICHELA MAPELLI

Definitive evidence that globular clusters (GCs) host intermediate-mass black holes (IMBHs) is elusive. Machine learning (ML) models trained… (see more) on GC simulations can in principle predict IMBH host candidates based on observable features. This approach has two limitations: first, an accurate ML model is expected to be a black box due to complexity; second, despite our efforts to realistically simulate GCs, the simulation physics or initial conditions may fail to fully reflect reality. Therefore our training data may be biased, leading to a failure in generalization on observational data. Both the first issue -- explainability/interpretability -- and the second -- out of distribution generalization and fairness -- are active areas of research in ML. Here we employ techniques from these fields to address them: we use the anchors method to explain an XGBoost classifier; we also independently train a natively interpretable model using Certifiably Optimal RulE ListS (CORELS). The resulting model has a clear physical meaning, but loses some performance with respect to XGBoost. We evaluate potential candidates in real data based not only on classifier predictions but also on their similarity to the training data, measured by the likelihood of a kernel density estimation model. This measures the realism of our simulated data and mitigates the risk that our models may produce biased predictions by working in extrapolation. We apply our classifiers to real GCs, obtaining a predicted classification, a measure of the confidence of the prediction, an out-of-distribution flag, a local rule explaining the prediction of XGBoost and a global rule from CORELS.

2024-04-08

The Astrophysical Journal (published)