Monthly Archives: December 2023
Workshop “Networks, Games and Risk”
Monday we had our workshop “Networks, Games and Risk“,
with Renaud Bourles (Centrale Marseille, Aix-Marseille School of Economics, and Institut Universitaire de France, France), Vincent Boucher (Université Laval, Québec, Canada), Federico Bobbio (Université de Montréal, Montréal, Canada), Leonie Baumann (McGill University, Montréal, Canada), Fallou Niakh (CREST, ENSAE, Institut Polytechnique de Paris, France) and Philipp Ratz (Université du Québec à Montréal, Montréal, Canada)
It was extremely interesting !
Apprentissage par renforcement, jeux et collision
Ce matin, Suzie Grondin nous expliquait les applications du RL (apprentissage par renforcement) en théorie des jeux, pour comprendre la collusion, pour la fin de son stage (6 mois de césure à l’ENSAE Paris) 😪 . Avec un lien avec le papier de Luc Rocher sur les approches adversariales, et une rapide introduction au “Offline-to-Online Reinforcement Learning”…
Merci à toute l’équipe (Philipp Ratz, François HU, Agathe Fernandes Machado, Dante Mata López) qui est venu l’écouter, ainsi que Louis Abraham… Superbe travail ! on veut un papier maintenant 😉 !
Melting contestation: insurance fairness and machine learning
Nice review of our paper , with Laurence Barry, on montrealethics.ai,
Machine learning tends to replace the actuary in the selection of features and the building of pricing models. However, avoiding subjective judgments thanks to automation does not necessarily mean that biases are removed. Nor does the absence of bias warrant fairness. This paper critically analyzes discrimination and insurance fairness with machine learning.
Melting contestation: insurance fairness and machine learning
The whole is greater than the sum of the parts
Good news: ou paper, A Sequentially Fair Mechanism for Multiple Sensitive Attributes, written with Philipp Ratz and François Hu will be presented in February in Vancouver, at the 38th Annual AAAI Conference on Artificial Intelligence. For a shorter version, there was a review on montrealethics.ai of the paper last week (as mentioned previously).
Also, last week also, the team launched the equipy python package, with codes used in the paper,
pip install equipy
EquiPy is a Python package implementing sequential fairness on the predicted outputs of Machine Learning models, when dealing with multiple sensitive attributes. This post-processing method progressively achieve fairness accross a set of sensitive features by leveraging multi-marginal Wasserstein barycenters, which extends the standard notion of Strong Demographic Parity to the case with multiple sensitive characteristics. This approach seamlessly extends to approximate fairness, enveloping a framework accommodating the trade-off between performance and unfairness.
(from the left to the right, Agathe, who just joint the PhD program, Suzie, MSc student at ENSAE, with us since May or June, Philipp, PhD student, François, postdoctoral fellow – and Dante, also postdoctoral fellow, in stochastic processes). According to Aristotle (or probably slightly misquoted),
the whole is greater than the sum of the parts
I couldn’t agree more !
Second workshop on fairness and discrimination in insurance
18 months ago, we organized a Workshop on fairness and discrimination in insurance, at Laval University (in Québec city), with Marie-Pier Côté. And we can now officially annonce that in 6 months, the second workshop will be organized. More to come soon…
A Sequentially Fair Mechanism for Multiple Sensitive Attributes
Nice review of our paper, with Philipp Ratz and François Hu, on montrealethics.ai.
Ask a group of people which biases in machine learning should be reduced, and you are likely to be showered with suggestions, making it difficult to decide where to start. To enable an objective discussion, we study a way to sequentially get rid of biases and propose a tool that can efficiently analyze the effects that the order of correction has on outcomes.
A Sequentially Fair Mechanism for Multiple Sensitive Attributes
Podcast: IA, biais et éthique en assurance
Lors de mon dernier passage à Paris, en France, j’en avais profité pour discuter avec Vivien, et enregistrer un podcast comme on dit en France, ou balado comme on dit ici. C’était l’occasion de revenir un peu sur le Manuel d’Assurance, sorti un an auparavant, et le livre Insurance, Biases, Discrimination and Fairness annoncé pour l’hiver prochain… Le podcast peut s’écouter sur youtube, et spotify
(image générée par ai-comic-factory)
Table ronde sur le risque sécheresse en France, à l’ENS Ker Lann
Jeudi 7 décembre, je participerai (en distanciel) à une “table ronde” sur le risque sécheresse en France, à l’École Normale Supérieure de Ker Lann, intitulée “enjeux actuels et futurs des sécheresses“. Comme on m’a demandé de présenter nos travaux récents, j’ai prévu quelques slides rapides…
[mise à jour] la conférence est en ligne sur youtube.