« La Relève ». Chaque mois, « Le Monde Campus » rencontre un jeune qui bouscule les normes dans son domaine. A 31 ans, la docteure en mathématiques s’attaque aux biais algorithmiques de l’intelligence artificielle et a reçu en 2024 un prix pour ses travaux.

This monograph studies the relations between two approaches using positive definite kernels: probabilistic methods using Gaussian processes, and non-probabilistic methods using reproducing kernel Hilb...

Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task. The main aim of ...

Optimal Transport is a foundational mathematical theory that connects optimization, partial differential equations, and probability. It offers a powerful framework for comparing probability distributi...

YouTube video by ML New Papers

An important feature of kernel mean embeddings (KME) is that the rate of convergence of the empirical KME to the true distribution KME can be bounded independently of the dimension of the space, prope...