One can also check google scholar.
J. Wenkmann, D. Garreau, On the variability of concept activation vectors [preprint] [code]
P.-A. Mattei, D. Garreau, Are ensembles getting better all the time? JMLR, in press [preprint] [code]
K. Mitsuzawa, D. Garreau, MMD-Flagger: Leveraging Maximum Mean Discrepancy to Detect Hallucinations [preprint] [code]
M. Taimeskhanov, R. Sicre, D. Garreau, CAM-based methods can see through walls (extended abstract), IJCAI [paper] [code]
M. Taimeskhanov, D. Garreau, Feature Attribution from First Principles [preprint] [code]
G. Visani, V. Stanzione, D. Garreau, GLEAMS: Bridging the Gap Between Local and Global Explanations, KDD Workshop on Human-Interpretable AI [preprint] [code]
M. Taimeskhanov, R. Sicre, D. Garreau, CAM-based methods can see through walls, ECML 2024 (best paper award) [preprint] [code]
G. Lopardo, F. Precioso, D. Garreau, Attention Meets Post-hoc Interpretability: A Mathematical Perspective , ICML 2024 [preprint] [code]
H. Fokkema, D. Garreau, T. van Erven, The Risks of Recourse in Binary Classification, AISTATS 2024 [paper] [code]
G. Lopardo, F. Precioso, D. Garreau, Faithful and Robust Local Interpretability for Textual Predictions [preprint] [code]
R. Catellier, S. Vaiter, D. Garreau, On the Robustness of Text Vectorizers, ICML 2023 [paper] [code]
H. Sénétaire, D. Garreau, J. Frellsen, P.-A. Mattei, Explainability as statistical inference, ICML 2023 [paper]
G. Lopardo, F. Precioso, D. Garreau, A Sea of Words: An In-Depth Analysis of Anchors for Text Data, AISTATS 2023 [paper] [code]
S. Bartels, W. Boomsma, J. Frellsen, D. Garreau, Kernel-Matrix Determinant Estimates from stopped Cholesky Decomposition, JMLR [paper] [code]
chapter 14 in Explainable Deep Learning AI: Methods and Challenges, Elsevier
B. Ly, S. Finsterbach, M. Nuñez-Garcia, P. Jaïs, D. Garreau, H. Cochet, M. Sermesant, Interpretable Prediction of Post-Infarct Ventricular Arrhythmia using Graph Convolutional Network, STACOM 13th Workshop on Statistical Atlases and Computational Modelling of the Heart, 2022 [paper]
G. Lopardo, D. Garreau, Comparing Feature Importance and Rule Extraction for Interpretability on Text Data, ICPR 2nd Workshop on Explainable and Ethical AI, 2022 [paper][code]
G. Lopardo, D. Garreau, F. Precioso, G. Ottosson, SMACE: A New Method for the Interpretability of Composite Decision Systems, ECML 2022 [paper] [code]
D. Garreau, How to scale hyperparameters for quickshift image segmentation, AISTATS 2022 [paper] [code]
D. Garreau, D. Mardaoui, What does LIME really see in images? ICML 2021 [paper] [supplementary] [code]
L. Rendsburg, D. Garreau, Comparison-based centrality measures, International Journal of Datascience and Analytics, 2021 [paper]
D. Mardaoui, D. Garreau, An Analysis of LIME for Text Data, AISTATS 2021 (oral presentation, top 10% of accepted papers) [paper] [supplementary] [code]
N. Keriven, D. Garreau, I. Poli, NEWMA: a new method for scalable model-free online change-point detection, IEEE Transactions on Signal Processing, 2020 [paper]
D. Garreau, U. von Luxburg, Explaining the Explainer: A First Theoretical Analysis of LIME, AISTATS 2020 [paper] [supplementary]
D. Garreau, U. von Luxburg, Looking Deeper into Tabular LIME [preprint] [code]
C. Tang, U. von Luxburg, When do random forests fail?, NeurIPS 2018 [paper]
S. Haghiri, D. Garreau, U. von Luxburg, Comparison-Based Random Forests, ICML 2018 [paper] [supplementary] [code]
F. Schoeller, M. Eskinazi, D. Garreau, Dynamics of the knowledge instinct: Effects of incoherence on the cognitive system, Cognitive Systems Research, 2018 [paper]
D. Garreau, S. Arlot, Consistent change-point detection with kernels, Electronic Journal of Statistics, 2018 [paper]
D. Garreau, Change-point Detection and Kernel Methods, PhD thesis [pdf]
D. Garreau, W. Jitkrittum, and M. Kanagawa, Large sample analysis of the median heuristic, [preprint]
D. Garreau, S. Arlot, Détection de ruptures multiples à noyaux, 48èmes Journées de Statistique de la SFdS [paper]
D. Garreau, R. Lajugie, S. Arlot, F. Bach, Metric learning for temporal sequence alignment, NeurIPS 2014 [paper]
I am incredibly grateful to have collaborated with the following people over the years:
Mickaël Eskinazi
Iacopo Poli