Catégorie
Other seminars
Date de tri

« Le Séminaire Palaisien » | Joon Kwon and Evgenii Chzhen on machine learning and statistics

Bandeau image
palaisien

« Le Séminaire Palaisien » | Joon Kwon and Evgenii Chzhen on machine learning and statistics

Lieu de l'événement
URL : https://bluejeans.com/9352872428/9913
Date de l'événement (intitulé)
6 October 2020 - 16.00
Chapo
Le Séminaire Palaisien gathers, every first Tuesday of the month, the vast research community of Saclay around statistics and machine learning.
Contenu
Corps de texte

Each seminar session is divided into 2 scientific presentations of 40 minutes each: 30 minutes of presentation and 10 minutes of questions.

Joon Kwon (INRAE) et Evgenii Chzhen (Université Paris-Saclay), will lead the session of October.

Nom de l'accordéon
« Unifying mirror descent and dual averaging » - Joon Kwon
Texte dans l'accordéon

We introduce and analyse a new family of algorithms which generalizes and unifies both the mirror descent and the dual averaging algorithms. In the framework of this family, we define a new algorithm for constrained optimization with the aim of combining the advantages of mirror descent and dual averaging. In practice, this new algorithm converges as fast as mirror descent and dual averaging, and in some situations greatly outperforms them. Besides, we demonstrate how our algorithms can also be applied to solving variational inequalities. 

This is joint work with Anatoli Juditsky and Eric Moulines.

Nom de l'accordéon
« Algorithmic Fairness in Classification and Regression » - Evgenii Chzhen
Texte dans l'accordéon

The goal of this talk is to introduce the audience to the problem of algorithmic fairness. I will provide a general overview on the topic, describe various available notions of fairness in classification and regression, and present main approaches to tackle this problem. I will also present some recent theoretical results both in classification and regression.

This talk is based on joint works with C. Denis, M. Hebiri, L. Oneto, and M. Pontil.