Jump to Content

Robust Domain Adaptation

Yishay Mansour
Annals of Mathematics and Artificial Intelligence, vol. 71 Issue 4 (2014), 365–380


We derive a generalization bound for domain adaptation by using the properties of robust algorithms. Our new bound depends on λ-shift, a measure of prior knowledge regarding the similarity of source and target domain distributions. Based on the generalization bound, we design SVM variants for binary classification and regression domain adaptation algorithms.