Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization
A doubly-anchored DRO framework whose ambiguity set is the intersection of $\phi$-divergence balls centered at the source law and a source-completed target reference law, the latter pairing the target covariate law with the source conditional law is introduced.
D. Kepplinger, Anand N. Vidyashankar
· 0 citations