Louis Béthune

14
Documents

Publications

Publications

Image document

DP-SGD Without Clipping: The Lipschitz Neural Network Way

Louis Béthune , Thomas Massena , Thibaut Boissin , Yannick Prudent , Corentin Friedrich et al.
ICLR 2024 - 12th International Conference on Learning Representations, 2024, Vienna (Austria), Austria
Communication dans un congrès hal-04610647 v1
Image document

On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective

Mathieu Serrurier , Franck Mamalet , Thomas Fel , Louis Béthune , Thibaut Boissin
Conference on Neural Information Processing Systems (NeurIPS), Neural Information Processing Systems Foundation, Dec 2023, New Orleans (Louisiana), United States
Communication dans un congrès hal-03693355 v3
Image document

A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation

Thomas Fel , Victor Boutin , Mazda Moayeri , Rémi Cadène , Louis Bethune et al.
Conference on Neural Information Processing Systems (NeurIPS), 2023, Dec 2023, New Orleans (Louisiana), United States
Communication dans un congrès hal-04391647 v1
Image document

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

Louis Béthune , Paul Novello , Thibaut Boissin , Guillaume Coiffier , Mathieu Serrurier et al.
40th International Conference on Machine Learning, Jul 2023, Honolulu, Hawaii, United States. pp.2245-2271, ⟨10.5555/3618408.3618504⟩
Communication dans un congrès hal-03977272 v2
Image document

Efficient circuit implementation for coined quantum walks on binary trees and application to reinforcement learning

Thomas Mullor , David Vigouroux , Louis Béthune
ACM/IEEE International Workshop on Quantum Computing @ 7th Symposium on Edge Computing (SEC 2022), Dec 2022, Seattle, United States. pp.436-443, ⟨10.1109/SEC54971.2022.00066⟩
Communication dans un congrès hal-03812297 v2
Image document

CRAFT: Concept Recursive Activation FacTorization for Explainability

Thomas Fel , Agustin Picard , Louis Bethune , Thibaut Boissin , David Vigouroux et al.
Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023., 2023, Vancouver, Canada
Communication dans un congrès hal-04049806 v1

Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks

Louis Béthune , Thibaut Boissin , Mathieu Serrurier , Franck Mamalet , Corentin Friedrich et al.
Advances in Neural Information Processing Systems, Nov 2022, New Orleans, United States. ⟨10.48550/arXiv.2104.05097⟩
Communication dans un congrès hal-03872080 v1

Xplique: A Deep Learning Explainability Toolbox

Thomas Fel , Lucas Hervier , David Vigouroux , Antonin Poche , Justin Plakoo et al.
The Conference on Computer Vision and Pattern Recognition, Workshop: Explainable Artificial Intelligence for Computer Vision (XAI4CV), Jun 2022, Nouvelle-Orléans, United States
Communication dans un congrès hal-03696248 v1

Gaussian Processes on Distributions based on Regularized Optimal Transport

François Bachoc , Louis Béthune , Alberto González-Sanz , Jean-Michel Loubes
26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), Apr 2023, Valencia, Spain. ⟨10.48550/arXiv.2210.06574⟩
Communication dans un congrès hal-03981114 v1
Image document

Deep learning with Lipschitz constraints

Louis Béthune
Artificial Intelligence [cs.AI]. Université de Toulouse, 2024. English. ⟨NNT : 2024TLSES014⟩
Thèse tel-04674274 v1