Search papers, labs, and topics across Lattice.
Département d’informatique et génie logiciel Université Laval Québec, Qc, Canada, LabHC, IUF, MALICE
2
0
4
2
Get generalization guarantees for your deep learning model without changing its architecture or training procedure by bounding its risk against a well-understood surrogate.
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.