AI RESEARCH

How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension

arXiv CS.LG

ArXi:2506.16704v3 Announce Type: replace We study a fundamental question of domain generalization: given a family of domains (i.e., data distributions), how many randomly sampled domains do we need to collect data from in order to learn a model that performs reasonably well on every seen and unseen domain in the family? We model this problem in the PAC framework and