Alex Hernández-García

sanad.abubaker@mila.quebec

Biography

Alex Hernandez-Garcia is an assistant professor at the Université de Montréal, a core academic member at Mila, IVADO professor and member of the Institut Courtois. His machine learning research is motivated by scientific applications to tackle the climate crisis and other societal challenges. In particular, a current focus of his work is active and generative machine learning to facilitate scientific discoveries, such as new materials and antibiotics. He also advocates for a critical examination of the impacts of artificial intelligence, is a strong proponent of open science and is active in initiatives about making science more inclusive, equitable, open, reproducible, transparent and environmentally conscious.

Current Students

Sanad Abu Baker

Research Intern - Université de Montréal

Tim Arni

Research Intern - Université de Montréal

tim.arni@mila.quebec

dionessa.biton@mila.quebec

Dionessa Biton

Master's Research - Université de Montréal

Minkyu Kim

Independent visiting researcher - KAIST

minkyu.kim@mila.quebec

Hyeonah Kim

Postdoctorate - Université de Montréal

Co-supervisor :

ethan.kreuzer@mila.quebec

hyeonah.kim@mila.quebec

Ethan Kreuzer

Master's Research - Université de Montréal

Principal supervisor :

Dominique Beaini

Pierre-Louis Lemaire

Collaborating researcher - Polytechnique Montréal Montréal

Co-supervisor :

David Rolnick

pierre-louis.lemaire@mila.quebec

Ameer Nizami

PhD - Concordia University

ameer.nizami@mila.quebec

Ola Onabola

PhD - Université de Montréal

walexi4great@gmail.com

Master's Research - Université de Montréal

celine.roget@mila.quebec

dounia.shaaban-kabakibo@mila.quebec

Dounia Shaaban Kabakibo

PhD - Université de Montréal

Principal supervisor :

Michel Côté

Divya Sharma

Postdoctorate - Université de Montréal

Principal supervisor :

divya.sharma@mila.quebec

Publications

GFlowNets for AI-Driven Scientific Discovery

Moksh Jain

Tristan Deleu

Jason Hartford

Cheng-Hao Liu

Tackling the most pressing problems for humanity, such as the climate crisis and the threat of global pandemics, requires accelerating the p… (see more)ace of scientific discovery. While science has traditionally relied on trial and error and even serendipity to a large extent, the last few decades have seen a surge of data-driven scientific discoveries. However, in order to truly leverage large-scale data sets and high-throughput experimental setups, machine learning methods will need to be further improved and better integrated in the scientific discovery pipeline. A key challenge for current machine learning methods in this context is the efficient exploration of very large search spaces, which requires techniques for estimating reducible (epistemic) uncertainty and generating sets of diverse and informative experiments to perform. This motivated a new probabilistic machine learning framework called GFlowNets, which can be applied in the modeling, hypotheses generation and experimental design stages of the experimental science loop. GFlowNets learn to sample from a distribution given indirectly by a reward function corresponding to an unnormalized probability, which enables sampling diverse, high-reward candidates. GFlowNets can also be used to form efficient and amortized Bayesian posterior estimators for causal models conditioned on the already acquired experimental data. Having such posterior models can then provide estimators of epistemic uncertainty and information gain that can drive an experimental design policy. Altogether, here we will argue that GFlowNets can become a valuable tool for AI-driven scientific discovery, especially in scenarios of very large candidate spaces where we have access to cheap but inaccurate measurements or to expensive but accurate measurements. This is a common setting in the context of drug and material discovery, which we use as examples throughout the paper.

2022-12-31

Digital Discovery (published)

arxiv.org

Hard-Constrained Deep Learning for Climate Downscaling

Paula Harder

Venkatesh Ramesh

Qidong Yang

Prasanna Sattegeri

D. Szwarcman

Campbell Watson

David Rolnick

The availability of reliable, high-resolution climate and weather data is important to inform long-term decisions on climate adaptation and … (see more)mitigation and to guide rapid responses to extreme events. Forecasting models are limited by computational costs and, therefore, often generate coarse-resolution predictions. Statistical downscaling, including super-resolution methods from deep learning, can provide an efficient method of upsampling low-resolution data. However, despite achieving visually compelling results in some cases, such models frequently violate conservation laws when predicting physical variables. In order to conserve physical quantities, here we introduce methods that guarantee statistical constraints are satisfied by a deep learning downscaling model, while also improving their performance according to traditional metrics. We compare different constraining approaches and demonstrate their applicability across different neural architectures as well as a variety of climate and weather data sets. Besides enabling faster and more accurate climate predictions through downscaling, we also show that our novel methodologies can improve super-resolution for satellite data and natural images data sets.

2022-12-31

Journal of Machine Learning Research (published)

arxiv.org

Diversifying Design of Nucleic Acid Aptamers Using Unsupervised Machine Learning

Siba Moussa

Michael Kilgour

Clara Jans

Miroslava Cuperlovic‐culf

Lena Simine

2022-08-09

ArXiv (preprint)

arxiv.org

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

Victor Schmidt

Alexandra Luccioni

Mélisande Teng

Tianyu Zhang

Alexia Reynaud

Sunand Raghupathi

Gautier Cosne

Adrien Juraver

Vahe Vardanyan

Climate change is a major threat to humanity, and the actions required to prevent its catastrophic consequences include changes in both poli… (see more)cy-making and individual behaviour. However, taking action requires understanding the effects of climate change, even though they may seem abstract and distant. Projecting the potential consequences of extreme climate events such as flooding in familiar places can help make the abstract impacts of climate change more concrete and encourage action. As part of a larger initiative to build a website that projects extreme climate events onto user-chosen photos, we present our solution to simulate photo-realistic floods on authentic images. To address this complex task in the absence of suitable training data, we propose ClimateGAN, a model that leverages both simulated and real data for unsupervised domain adaptation and conditional image generation. In this paper, we describe the details of our framework, thoroughly evaluate components of our architecture and demonstrate that our model is capable of robustly generating photo-realistic flooding.

2022-04-24

International Conference on Learning Representations (Accept (Poster))

openreview.net

Generating physically-consistent high-resolution climate data with hard-constrained neural networks

Paula Harder

Qidong Yang

Venkatesh Ramesh

Prasanna Sattegeri

Campbell Watson

D. Szwarcman

David Rolnick

The availability of reliable, high-resolution climate and weather data is important to inform long-term decisions on climate adaptation and … (see more)mitigation and to guide rapid responses to extreme events. Forecasting models are limited by computational costs and therefore often can only make coarse resolution predictions. Statistical downscaling can provide an efficient method of upsampling low-resolution data. In this field, deep learning has been applied successfully, often us-ing image super-resolution methods from computer vision. Despite achieving visually compelling results in some cases, such models often violate conservation laws when predicting physical variables. In order to conserve important physical quantities, we develop methods that guarantee physical constraints are satisfied by a deep downscaling model while also increasing their performance according to traditional metrics. We introduce two ways of constraining the network: A renor-malization layer added to the end of the neural network and a successive approach that scales with increasing upsampling factors. We show the applicability of our methods across different popular architectures and upsampling factors using ERA5 reanalysis data.

2021-12-31

arXiv.org (preprint)