Collection 10e Journée Statistique et Informatique pour la Science des Données à Paris-Saclay

The aim of this workshop is to bring together mathematicians and computer scientists around some talks on recent results from statistics, machine learning, and more generally data science research. Various topics in machine learning, optimization, deep learning, optimal transport, fairness, statistics will be presented. This workshop is particularly intended for doctoral and post-doctoral researchers.

Organizer(s) Evgenii Chzhen, Erwan Le Pennec
Date(s) 01/04/2025 - 01/04/2025
linked URL https://indico.math.cnrs.fr/event/14016/

All the collection videos (6)

52:40

published on April 10, 2025

Topics in Algorithmic Fairness

By Solenne Gaucher

56:50

published on April 10, 2025

Deep Out-of-the-distribution Uncertainty Quantification in for Data (Science) Scientists

By Nicolas Vayatis

50:52

published on April 10, 2025

Slow Convergence of Stochastic Optimization Algorithms Without Derivatives Is Avoidable

By Anne Auger

47:51

published on April 10, 2025

Fair Classifiers via Transferable Representations

By Charlotte Laclau

52:04

published on April 10, 2025

Optimal Rates of Exact Recovery of the Matching Map

By Arshak Minasyan

57:24

published on April 10, 2025

Training Overparametrized Neural Networks: Early Alignment Phenomenon and Simplicity Bias

By Etienne Boursier

Mathematics
and Interactions

Not Only Scalar Curvature Seminar

Geometric structures and discrete group actions / Structures géométriques et actions de groupes discrets

Misha Gromov : Mathematical Description of Biological Structures

Applications of NonCommutative Geometry to Gauge Theories, Field Theories, and Quantum Space-Time / Applications de la Géométrie Non Commutative aux Théories de Jauge, à la Théorie des Champs et aux Espaces-Temps Quantiques

Collection 10e Journée Statistique et Informatique pour la Science des Données à Paris-Saclay

Topics in Algorithmic Fairness

Deep Out-of-the-distribution Uncertainty Quantification in for Data (Science) Scientists

Slow Convergence of Stochastic Optimization Algorithms Without Derivatives Is Avoidable

Fair Classifiers via Transferable Representations

Optimal Rates of Exact Recovery of the Matching Map

Training Overparametrized Neural Networks: Early Alignment Phenomenon and Simplicity Bias

Symbolic language models: applications and interpretability - lecture 2

Symbolic language models: applications and interpretability - lecture 1

Maths and AI

Are adaptive robust confidence intervals possible?

From robust tests to robust Bayes-like posterior distribution