2 code implementations • 27 Sep 2023 • Antoine de Mathelin, François Deheeger, Mathilde Mougeot, Nicolas Vayatis
Under this paradigm, the epistemic uncertainty is described by the weight distribution of maximal entropy that produces neural networks "consistent" with the training observations.
no code implementations • 8 Apr 2023 • Antoine de Mathelin, Francois Deheeger, Mathilde Mougeot, Nicolas Vayatis
We derive a simple and practical approach to produce such ensembles, based on an original anti-regularization term penalizing small weights and a control process of the weight increase which maintains the in-distribution loss under an acceptable threshold.
1 code implementation • 9 Sep 2022 • Antoine de Mathelin, Francois Deheeger, Mathilde Mougeot, Nicolas Vayatis
Bias in datasets can be very detrimental for appropriate statistical estimation.
1 code implementation • 28 Dec 2021 • Sankalp Gilda, Antoine de Mathelin, Sabine Bellstedt, Guillaume Richard
The prevalent paradigm of machine learning today is to use past observations to predict future ones.
1 code implementation • 17 Dec 2021 • Fouad Oubari, Antoine de Mathelin, Rodrigue Décatoire, Mathilde Mougeot
Designing new industrial materials with desired properties can be very expensive and time consuming.
1 code implementation • 7 Jul 2021 • Antoine de Mathelin, Mounir Atiq, Guillaume Richard, Alejandro de la Concha, Mouad Yachouti, François Deheeger, Mathilde Mougeot, Nicolas Vayatis
In this paper, we introduce the ADAPT library, an open source Python API providing the implementation of the main transfer learning and domain adaptation methods.
2 code implementations • ICLR 2022 • Antoine de Mathelin, Francois Deheeger, Mathilde Mougeot, Nicolas Vayatis
The goal of the paper is to design active learning strategies which lead to domain adaptation under an assumption of Lipschitz functions.
2 code implementations • 15 Jun 2020 • Antoine de Mathelin, Guillaume Richard, Francois Deheeger, Mathilde Mougeot, Nicolas Vayatis
We present a novel instance-based approach to handle regression tasks in the context of supervised domain adaptation under an assumption of covariate shift.