Search Results for author: Eloïse Berthier

Found 3 papers, 0 papers with code

CLIP-QDA: An Explainable Concept Bottleneck Model

no code implementations30 Nov 2023 Rémi Kazmierczak, Eloïse Berthier, Goran Frehse, Gianni Franchi

In this paper, we introduce an explainable algorithm designed from a multi-modal foundation model, that performs fast and explainable image classification.

Image Classification

On Double Descent in Reinforcement Learning with LSTD and Random Features

no code implementations9 Oct 2023 David Brellmann, Eloïse Berthier, David Filliat, Goran Frehse

We identify the ratio between the number of parameters and the number of visited states as a crucial factor and define over-parameterization as the regime when it is larger than one.

reinforcement-learning Reinforcement Learning (RL)

Amplifying Rényi Differential Privacy via Shuffling

no code implementations11 Jul 2019 Eloïse Berthier, Sai Praneeth Karimireddy

Differential privacy is a useful tool to build machine learning models which do not release too much information about the training data.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.