Sébastien Destercke

Compact set-valued deep ensembling in multi-class classification

This paper tackles visible challenges in deep ensemble learning, where deep neural networks serve as ensemble members: training and storage burdens, and robustness of cautious (set-valued) predictions targeting multiple utilities, which may involve reward-sensitivity. To mitigate the training and storage burdens, we pr...

Robust Multi-label Classification via Preference Learning

SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors

SPACR (Single-Pass Adaptive Conformal Regressor), a novel method for directly training uncertainty-aware regressors within a differentiable loss, jointly optimizes accuracy, efficiency, and validity without batch-splitting or a predefined confidence level during training.