4 papers · 1 filter
Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators
Pierre Nodet, Thomas George
We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources…
MIFair: A Mutual-Information Framework for Intersectionality and Multiclass Fairness
Jeanne Monnier, Thomas George, Frédéric Guyard +2
Fairness in machine learning remains challenging due to its ethical complexity, the absence of a universal definition, and the need for context-specific bias metrics. Existing meth…
Calibration improves detection of mislabeled examples
Ilies Chibane, Thomas George, Pierre Nodet +1
Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to de…
Mislabeled examples detection viewed as probing machine learning models: concepts, survey and extensive benchmark
Thomas George, Pierre Nodet, Alexis Bondu +1
Mislabeled examples are ubiquitous in real-world machine learning datasets, advocating the development of techniques for automatic detection. We show that most mislabeled detection…