Preprint
Aug 2026
Distribution-Free Halfspace Testing with Samples
It is proved that testing is no more efficient than learning for halfspaces in the distribution-free sample-based model, and it is established that two-sided halfspace testers in this model have no advantage over one-sided testers.
Xi Chen, Renato Ferreira Pinto, Nathaniel Harms et al.
· 0 citations