2 code implementations • 9 Apr 2024 • Roman Malinowski, Emmanuelle Sarrazin, Loïc Dumas, Emmanuel Dubois, Sébastien Destercke
To the best of our knowledge, this is the first method creating disparity confidence intervals based on the cost volume.
1 code implementation • ECSQARU 2023 2023 • Vu-Linh Nguyen, Haifei Zhang, Sébastien Destercke
A possible approach to obtain set-valued predictions is to learn for each query instance a probability set (a. k. a.
1 code implementation • 2 May 2022 • Yonatan Carlos Carranza Alarcón, Sébastien Destercke
In this paper, we consider the problem of making distributionally robust, skeptical inferences for the multi-label problem, or more generally for Boolean vectors.
no code implementations • 15 Jul 2021 • Yonatan Carlos Carranza Alarcón, Sébastien Destercke
We present two different strategies to extend the classical multi-label chaining approach to handle imprecise probability estimates.
no code implementations • 28 Jan 2021 • Soundouss Messoudi, Sébastien Destercke, Sylvain Rousseau
There are relatively few works dealing with conformal prediction for multi-task learning issues, and this is particularly true for multi-target regression.
no code implementations • 13 Dec 2019 • Zied Bouraoui, Antoine Cornuéjols, Thierry Denœux, Sébastien Destercke, Didier Dubois, Romain Guillaume, João Marques-Silva, Jérôme Mengin, Henri Prade, Steven Schockaert, Mathieu Serrurier, Christel Vrain
Some common concerns are identified and discussed such as the types of used representation, the roles of knowledge and data, the lack or the excess of information, or the need for explanations and causal understanding.
no code implementations • 31 Aug 2019 • Vu-Linh Nguyen, Sébastien Destercke, Eyke Hüllermeier
In this paper, we advocate a distinction between two different types of uncertainty, referred to as epistemic and aleatoric, in the context of active learning.
no code implementations • 5 Jan 2018 • Olivier Cailloux, Sébastien Destercke
Much has been written however on different models of preferences.