AI RESEARCH

Point-Identification of a Robust Predictor Under Latent Shift with Imperfect Proxies

arXiv CS.LG

ArXi:2603.15158v1 Announce Type: new Addressing the domain adaptation problem becomes challenging when distribution shifts across domains stem from latent confounders that affect both covariates and outcomes. Existing proxy-based approaches that address latent shift rely on a strong completeness assumption to uniquely determine (point-identify) a robust predictor. Completeness requires that proxies have sufficient information about variations in latent confounders.