5 citations · 19 across the 15 of their papers we have counts for
16 papers
Muon Is Theoretically Wrong For Convolutions, But Empirically Effective
Thibaut Boissin, Thomas Massena, Mathieu Serrurier +1
Muon, an optimizer known for its efficiency, has a clear interpretation for matrix-valued updates, but convolutional kernels are stored as four-dimensional tensors. Standard implem…
Orthogonium : A Unified, Efficient Library of Orthogonal and 1-Lipschitz Building Blocks
Thibaut Boissin, Franck Mamalet, Valentin Lafargue +1
Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generativ…
Back to the Baseline: Examining Baseline Effects on Explainability Metrics
Agustin Martin Picard, Thibaut Boissin, Varshini Subhash +2
Attribution methods are among the most prevalent techniques in Explainable Artificial Intelligence (XAI) and are usually evaluated and compared using Fidelity metrics, with Inserti…
Turbo-Muon: Almost-Orthogonal Pre-Conditioning for Fast Muon Updates
Thibaut Boissin, Thomas Massena, Franck Mamalet +1
Orthogonality-based optimizers, such as Muon, have recently shown strong performance across large-scale training and community-driven efficiency challenges. However, these methods…
Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
Thomas Massena, Léo andéol, Thibaut Boissin +4
Conformal Prediction (CP) has proven to be an effective post-hoc method for improving the trustworthiness of neural networks by providing prediction sets with finite-sample guarant…
An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
Thibaut Boissin, Franck Mamalet, Thomas Fel +3
Orthogonal convolutional layers are valuable components in multiple areas of machine learning, such as adversarial robustness, normalizing flows, GANs, and Lipschitz-constrained mo…
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception
Drew Linsley, Pinyuan Feng, Thibaut Boissin +4
Deep neural networks (DNNs) are known to have a fundamental sensitivity to adversarial attacks, perturbations of the input that are imperceptible to humans yet powerful enough to c…
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Thomas Fel, Thibaut Boissin, Victor Boutin +9
Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability.…
DP-SGD Without Clipping: The Lipschitz Neural Network Way
Louis Bethune, Thomas Massena, Thibaut Boissin +6
State-of-the-art approaches for training Differentially Private (DP) Deep Neural Networks (DNN) face difficulties to estimate tight bounds on the sensitivity of the network's layer…
Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks
Louis Bethune, Paul Novello, Thibaut Boissin +4
We propose a new method, dubbed One Class Signed Distance Function (OCSDF), to perform One Class Classification (OCC) by provably learning the Signed Distance Function (SDF) to the…
CRAFT: Concept Recursive Activation FacTorization for Explainability
Thomas Fel, Agustin Picard, Louis Bethune +5
Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explaina…
Xplique: A Deep Learning Explainability Toolbox
Thomas Fel, Lucas Hervier, David Vigouroux +12
Today's most advanced machine-learning models are hardly scrutable. The key challenge for explainability methods is to help assisting researchers in opening up these black boxes, b…
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
Mathieu Serrurier, Franck Mamalet, Thomas Fel +2
Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating…
Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks
Louis Béthune, Thibaut Boissin, Mathieu Serrurier +3
Lipschitz constrained networks have gathered considerable attention in the deep learning community, with usages ranging from Wasserstein distance estimation to the training of cert…
Fairness seen as Global Sensitivity Analysis
Clément Bénesse, Fabrice Gamboa, Jean-Michel Loubes +1
Ensuring that a predictor is not biased against a sensible feature is the key of Fairness learning. Conversely, Global Sensitivity Analysis is used in numerous contexts to monitor…
Achieving robustness in classification using optimal transport with hinge regularization
Mathieu Serrurier, Franck Mamalet, Alberto González-Sanz +3
Adversarial examples have pointed out Deep Neural Networks vulnerability to small local noise. It has been shown that constraining their Lipschitz constant should enhance robustnes…