Portrait de Yashar Hezaveh

Yashar Hezaveh

Membre académique associé

Professeur adjoint, Université de Montréal, Département de physique

Sujets de recherche

Apprentissage de représentations

Apprentissage profond

Vision par ordinateur

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

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Laurence Perreault-Levasseur

Doctorat - UdeM

Co-superviseur⋅e :

Laurence Perreault-Levasseur

Stagiaire de recherche - UdeM

Superviseur⋅e principal⋅e :

Laurence Perreault-Levasseur

Maîtrise recherche - McGill

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Laurence Perreault-Levasseur

Doctorat - UdeM

Co-superviseur⋅e :

Laurence Perreault-Levasseur

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Laurence Perreault-Levasseur

Parker Levesque

Maîtrise recherche - UdeM

Co-superviseur⋅e :

Pierre-Luc Bacon

Maîtrise recherche - UdeM

Co-superviseur⋅e :

Laurence Perreault-Levasseur

Sacha Perry-Fagant

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Laurence Perreault-Levasseur

Postdoctorat - UdeM

Co-superviseur⋅e :

Laurence Perreault-Levasseur

Maîtrise recherche - McGill

Postdoctorat - McGill

Superviseur⋅e principal⋅e :

Laurence Perreault-Levasseur

Postdoctorat - UdeM

Co-superviseur⋅e :

Pierre-Luc Bacon

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Laurence Perreault-Levasseur

Publications

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… (voir plus) 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 (publié)

Searching for Strong Gravitational Lenses

Cameron Lemon

Frederic Courbin

Anupreeta More

Paul Schechter

Raoul Cañameras

Ludovic Delchambre

Calvin Leung

Yiping Shu

Chiara Spiniello

Jonas Klüter

Richard G. McMahon

2024-02-20

Space Science Reviews (publié)

On Diffusion Modeling for Anomaly Detection

Victor Livernoche

Siamak Ravanbakhsh

Known for their impressive performance in generative modeling, diffusion models are attractive candidates for density-based anomaly detectio… (voir plus)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.

2024-01-15

ICLR.cc/2024/Conference (spotlight)

Caustics: A Python Package for Accelerated Strong Gravitational Lensing Simulations

M. J. Yantovski-Barth

Landung Setiawan

Cordero Core

Charles Wilson

Gabriel Missael Barco

Laurence Perreault-Levasseur

2023-12-31

J. Open Source Softw. (publié)

Extended Lyman-alpha emission towards the SPT2349-56 protocluster at $z=4.3$

Yordanka Apostolovski

Manuel Aravena

Timo Anguita

Matthieu Béthermin

James R. Burgoyne

Scott Chapman

C. Breuck

Anthony R Gonzalez

Max Gronke

Lucia Guaita

Ryley Hill

Sreevani Jarugula

E. Johnston

M. Malkan

Desika Narayanan

Cassie Reuter

Manuel Solimano

Justin Spilker

Nikolaus Sulzenauer … (voir 3 de plus)

Joaquin Vieira

David Vizgan

Axel Weiß

Deep spectroscopic surveys with the Atacama Large Millimeter/submillimeter Array (ALMA) have revealed that some of the brightest infrared so… (voir plus)urces in the sky correspond to concentrations of submillimeter galaxies (SMGs) at high redshift. Among these, the SPT2349-56 protocluster system is amongst the most extreme examples given its high source density and integrated star formation rate. We conducted a deep Lyman-alpha line emission survey around SPT2349-56 using the Multi-Unit Spectroscopic Explorer (MUSE) at the Very Large Telescope (VLT) in order to characterize this uniquely dense environment. Taking advantage of the deep three-dimensional nature of this survey, we performed a sensitive search for Lyman-alpha emitters (LAEs) toward the core and northern extension of the protocluster, which correspond to the brightest infrared regions in this field. Using a smoothed narrowband image extracted from the MUSE datacube around the protocluster redshift, we searched for possible extended structures. We identify only three LAEs at

2023-12-19

Astronomy & Astrophysics (publié)

Active learning meets fractal decision boundaries: a cautionary tale from the Sitnikov three-body problem

Mario Pasquato

Alessandro A. Trani

Laurence Perreault-Levasseur

Chaotic systems such as the gravitational N-body problem are ubiquitous in astronomy. Machine learning (ML) is increasingly deployed to pred… (voir plus)ict the evolution of such systems, e.g. with the goal of speeding up simulations. Strategies such as active Learning (AL) are a natural choice to optimize ML training. Here we showcase an AL failure when predicting the stability of the Sitnikov three-body problem, the simplest case of N-body problem displaying chaotic behavior. We link this failure to the fractal nature of our classification problem's decision boundary. This is a potential pitfall in optimizing large sets of N-body simulations via AL in the context of star cluster physics, galactic dynamics, or cosmology.

2023-11-28

ArXiv (prépublication)

Bayesian Imaging for Radio Interferometry with Score-Based Priors

No'e Dia

M. J. Yantovski-Barth

Micah Bowles

A. Scaife

Laurence Perreault-Levasseur

U. Montŕeal

Ciela Institute

Flatiron Institute

2023-11-28

ArXiv (prépublication)

Learning an Effective Evolution Equation for Particle-Mesh Simulations Across Cosmologies

Laurence Perreault-Levasseur

Carolina Cuesta-lazaro

C. Modi

2023-11-28

ArXiv (prépublication)

The search for the lost attractor

Mario Pasquato

Syphax Haddad

Pierfrancesco Di Cintio

No'e Dia

Mircea Petrache

Ugo Niccolo Di Carlo

Alessandro A. Trani

Laurence Perreault-Levasseur

2023-11-26

ArXiv (prépublication)

Score-Based Likelihood Characterization for Inverse Problems in the Presence of Non-Gaussian Noise

Laurence Perreault-Levasseur

Likelihood analysis is typically limited to normally distributed noise due to the difficulty of determining the probability density function… (voir plus) of complex, high-dimensional, non-Gaussian, and anisotropic noise. This work presents Score-based LIkelihood Characterization (SLIC), a framework that resolves this issue by building a data-driven noise model using a set of noise realizations from observations. We show that the approach produces unbiased and precise likelihoods even in the presence of highly non-Gaussian correlated and spatially varying noise. We use diffusion generative models to estimate the gradient of the probability density of noise with respect to data elements. In combination with the Jacobian of the physical model of the signal, we use Langevin sampling to produce independent samples from the unbiased likelihood. We demonstrate the effectiveness of the method using real data from the Hubble Space Telescope and James Webb Space Telescope.

2023-11-02

NeurIPS.cc/2023/Workshop/Deep_Inverse (poster)

Posterior Sampling of the Initial Conditions of the Universe from Non-linear Large Scale Structures using Score-Based Generative Models

Matthew Ho

Laurence Perreault-Levasseur

Shirley Ho

Benjamin Wandelt

Reconstructing the initial conditions of the universe is a key problem in cosmology. Methods based on simulating the forward evolution of th… (voir plus)e universe have provided a way to infer initial conditions consistent with present-day observations. However, due to the high complexity of the inference problem, these methods either fail to sample a distribution of possible initial density fields or require significant approximations in the simulation model to be tractable, potentially leading to biased results. In this work, we propose the use of score-based generative models to sample realizations of the early universe given present-day observations. We infer the initial density field of full high-resolution dark matter N-body simulations from the present-day density field and verify the quality of produced samples compared to the ground truth based on summary statistics. The proposed method is capable of providing plausible realizations of the early universe density field from the initial conditions posterior distribution marginalized over cosmological parameters and can sample orders of magnitude faster than current state-of-the-art methods.

2023-10-03

Monthly Notices of the Royal Astronomical Society: Letters (publié)

Time Delay Cosmography with a Neural Ratio Estimator

Ève Campeau-Poirier

Laurence Perreault-Levasseur

We explore the use of a Neural Ratio Estimator (NRE) to determine the Hubble constant (…

2023-09-26

ArXiv (prépublication)