Laurence Perreault-Levasseur

tara.akhoundsadegh@mila.quebec

Biographie

Laurence Perreault-Levasseur est titulaire de la Chaire de recherche du Canada en cosmologie numérique et intelligence artificielle. Professeure agrégée à l'Université de Montréal et membre principale de Mila, elle concentre ses travaux sur le développement et l'application des méthodes d'apprentissage automatique à la cosmologie.

Elle est également chercheuse invitée à l'Institut Flatiron de New York. Auparavant, elle a été chercheuse Flatiron au Center for Computational Astrophysics de ce même institut, ainsi que chercheuse postdoctorale KIPAC à l'Université Stanford. Laurence a obtenu son doctorat à l'Université de Cambridge, où ses recherches ont porté sur les applications des théories effectives des champs ouverts au formalisme de l'inflation. Elle détient un baccalauréat et une maîtrise de l'Université McGill.

Étudiants actuels

Tara Akhound-Sadegh

Doctorat - McGill

Superviseur⋅e principal⋅e :

Siamak Ravanbakhsh

Missael Barco

Doctorat - UdeM

Co-superviseur⋅e :

missael-gabriel.barco@mila.quebec

Misha Barth

Doctorat - UdeM

Superviseur⋅e principal⋅e :

michael.barth@mila.quebec

mohammed.chamma@mila.quebec

Mohammed Chamma

Postdoctorat - McGill

Doctorat - UdeM

Co-superviseur⋅e :

andreas.filipp@umontreal.ca

Ronan Legin

Doctorat - UdeM

Superviseur⋅e principal⋅e :

ronan.legin@mila.quebec

michael.matesic@mila.quebec

Michael Matesic

Doctorat - UdeM

guillaume.payeur@mail.mcgill.ca

Guillaume Payeur

Doctorat - UdeM

Maîtrise recherche - UdeM

Superviseur⋅e principal⋅e :

nicolas.payot@mila.quebec

Sacha Perry-Fagant

Doctorat - UdeM

Co-superviseur⋅e :

sacha.perry-fagant@mila.quebec

sammy.sharief@mila.quebec

Salma Salhi

Doctorat - UdeM

salhi.salma@mila.quebec

Ketan Sand

Postdoctorat - McGill

ketan.sand@mila.quebec

Sammy Nasser Sharief

Maîtrise recherche - UdeM

Nolan Smyth

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

nolan.smyth@mila.quebec

Yitian Sun

Postdoctorat - McGill

Co-superviseur⋅e :

yitian.sun@mila.quebec

Aya Tessier

Maîtrise recherche - UdeM

aya.astro.21@gmail.com

Justine Zeghal

Postdoctorat - UdeM

Co-superviseur⋅e :

justine.zeghal@mila.quebec

Publications

Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines

Alexandre Adam

MAX WELLING

Modeling strong gravitational lenses in order to quantify the distortions in the images of background sources and to reconstruct the mass de… (voir plus)nsity in the foreground lenses has been a difficult computational challenge. As the quality of gravitational lens images increases, the task of fully exploiting the information they contain becomes computationally and algorithmically more difficult. In this work, we use a neural network based on the Recurrent Inference Machine (RIM) to simultaneously reconstruct an undistorted image of the background source and the lens mass density distribution as pixelated maps. The method iteratively reconstructs the model parameters (the image of the source and a pixelated density map) by learning the process of optimizing the likelihood given the data using the physical model (a ray-tracing simulation), regularized by a prior implicitly learned by the neural network through its training data. When compared to more traditional parametric models, the proposed method is significantly more expressive and can reconstruct complex mass distributions, which we demonstrate by using realistic lensing galaxies taken from the IllustrisTNG cosmological hydrodynamic simulation.

2023-06-26

The Astrophysical Journal (publié)

A Framework for Obtaining Accurate Posteriors of Strong Gravitational Lensing Parameters with Flexible Priors and Implicit Likelihoods using Density Estimation

Ronan Legin

Benjamin Wandelt

We report the application of implicit likelihood inference to the prediction of the macro-parameters of strong lensing systems with neural n… (voir plus)etworks. This allows us to perform deep learning analysis of lensing systems within a well-defined Bayesian statistical framework to explicitly impose desired priors on lensing variables, to obtain accurate posteriors, and to guarantee convergence to the optimal posterior in the limit of perfect performance. We train neural networks to perform a regression task to produce point estimates of lensing parameters. We then interpret these estimates as compressed statistics in our inference setup and model their likelihood function using mixture density networks. We compare our results with those of approximate Bayesian neural networks, discuss their significance, and point to future directions. Based on a test set of 100,000 strong lensing simulations, our amortized model produces accurate posteriors for any arbitrary confidence interval, with a maximum percentage deviation of

2023-01-18

The Astrophysical Journal (publié)

Posterior samples of source galaxies in strong gravitational lenses with score-based priors

Alexandre Adam

Adam Coogan

Nikolay Malkin

Ronan Legin

Yoshua Bengio

Inferring accurate posteriors for high-dimensional representations of the brightness of gravitationally-lensed sources is a major challenge,… (voir plus) in part due to the difficulties of accurately quantifying the priors. Here, we report the use of a score-based model to encode the prior for the inference of undistorted images of background galaxies. This model is trained on a set of high-resolution images of undistorted galaxies. By adding the likelihood score to the prior score and using a reverse-time stochastic differential equation solver, we obtain samples from the posterior. Our method produces independent posterior samples and models the data almost down to the noise level. We show how the balance between the likelihood and the prior meet our expectations in an experiment with out-of-distribution data.

2022-11-06

ArXiv (prépublication)

GaMPEN: A Machine Learning Framework for Estimating Bayesian Posteriors of Galaxy Morphological Parameters

Aritra Ghosh

C. M. Urry

Amrit Rau

Miles Cranmer

Kevin Schawinski

Dominic Stark

Chuan Tian

Ryan Ofman

Tonima Tasnim Ananna

Connor Auge

N. Cappelluti

D. B. Sanders

Ezequiel Treister

We introduce a novel machine-learning framework for estimating the Bayesian posteriors of morphological parameters for arbitrarily large num… (voir plus)bers of galaxies. The Galaxy Morphology Posterior Estimation Network (GaMPEN) estimates values and uncertainties for a galaxy’s bulge-to-total-light ratio (L B /L T ), effective radius (R e ), and flux (F). To estimate posteriors, GaMPEN uses the Monte Carlo Dropout technique and incorporates the full covariance matrix between the output parameters in its loss function. GaMPEN also uses a spatial transformer network (STN) to automatically crop input galaxy frames to an optimal size before determining their morphology. This will allow it to be applied to new data without prior knowledge of galaxy size. Training and testing GaMPEN on galaxies simulated to match z 0.25 galaxies in Hyper Suprime-Cam Wide g-band images, we demonstrate that GaMPEN achieves typical errors of 0.1 in L B /L T , 0.″17 (∼7%) in R e , and 6.3 × 104 nJy (∼1%) in F. GaMPEN's predicted uncertainties are well calibrated and accurate (5% deviation)—for regions of the parameter space with high residuals, GaMPEN correctly predicts correspondingly large uncertainties. We a

2022-07-31

The Astrophysical Journal (publié)

Bayesian Neural Networks

Tom Charnock

François Lanusse

In recent times, neural networks have become a powerful tool for the analysis of complex and abstract data models. However, their introducti… (voir plus)on intrinsically increases our uncertainty about which features of the analysis are model-related and which are due to the neural network. This means that predictions by neural networks have biases which cannot be trivially distinguished from being due to the true nature of the creation and observation of data or not. In order to attempt to address such issues we discuss Bayesian neural networks: neural networks where the uncertainty due to the network can be characterised. In particular, we present the Bayesian statistical framework which allows us to categorise uncertainty in terms of the ingrained randomness of observing certain data and the uncertainty from our lack of knowledge about how data can be created and observed. In presenting such techniques we show how errors in prediction by neural networks can be obtained in principle, and provide the two favoured methods for characterising these errors. We will also describe how both of these methods have substantial pitfalls when put into practice, highlighting the need for other statistical techniques to truly be able to do inference when using neural networks.

2022-02-05

Artificial Intelligence for High Energy Physics (publié)

Machine Learning Advantages in Canadian Astrophysics

Kim Venn

Sébastien Fabbro

Adrian Liu

Gwendolyn Eadie

Sara Ellison

Joanna Woo

JJ Kavelaars

Kwang Moo Yi

Renée Hložek

Jo Bovy

Hossen Teimoorinia

Siamak Ravanbakhsh

Locke Spencer

The application of machine learning (ML) methods to the analysis of astrophysical datasets is on the rise, particularly as the computing pow… (voir plus)er and complex algorithms become more powerful and accessible. As the field of ML enjoys a continuous stream of breakthroughs, its applications demonstrate the great potential of ML, ranging from achieving tens of millions of times increase in analysis speed (e.g., modeling of gravitational lenses or analysing spectroscopic surveys) to solutions of previously unsolved problems (e.g., foreground subtraction or efficient telescope operations). The number of astronomical publications that include ML has been steadily increasing since 2010.
With the advent of extremely large datasets from a new generation of surveys in the 2020s, ML methods will become an indispensable tool in astrophysics. Canada is an unambiguous world leader in the development of the field of machine learning, attracting large investments and skilled researchers to its prestigious AI Research Institutions. This provides a unique opportunity for Canada to also be a world leader in the application of machine learning in the field of astrophysics, and foster the training of a new generation of highly skilled researchers.

2018-12-31

Zenodo (publié)