Amaury Habrard

A derandomization framework for stochastic majority votes is proposed that derives two families of high-probability generalization bounds, covering both data-independent and data-dependent constructions of the ensemble, which naturally lead to a self-bounding learning algorithm optimizing deterministic majority vote guarantees.

Finally, a PAC-Bayesian framework bridges the gap in fairness generalization guarantees for both stochastic and deterministic classifiers, offering a path to provably fair AI.