Publications & preprints
-
DP-SGD Without Clipping:
the Lipschitz neural network way International Conference on Learning Representations (ICLR) 2024 -
-
Robust One-Class Classification
with signed distance function using 1-Lipschitz neural networks International Conference on Machine Learning (ICML), 2023 -
On the explainable properties of 1-Lipschitz Neural Networks:
an optimal transport perspective Neural Information Processing Systems (NeurIPS), 2023 -
CRAFT
Concept Recursive Activation FacTorization for Explainability Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 -
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
Neural Information Processing Systems (NeurIPS), 2023 -
Gaussian Processes on Distributions
based on regularized optimal transport Artificial Intelligence and Statistics Conference (AISTATS), 2023 -
Pay attention to your loss:
understanding misconceptions about Lipschitz neural networks Neural Information Processing Systems (NeurIPS), 2022 -
-
Predicting the Generalization Ability of a Few-Shot Classifier
Artificial Intelligence, MDPI Information -
Hierarchical and Unsupervised Graph Representation Learning
with Loukas's Coarsening Efficient Graph Algorithms in Machine Learning, MDPI Algorithms
subscribe via RSS