The balancing principle for parameter choice in distance-regularized domain adaptation

Part of Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

Paper Supplemental

Bibtek download is not available in the pre-proceeding


Authors

Werner Zellinger, Natalia Shepeleva, Marius-Constantin Dinu, Hamid Eghbal-zadeh, Hoan Nguyen, Bernhard Nessler, Sergei Pereverzyev, Bernhard A. Moser

Abstract

We address the unsolved algorithm design problem of choosing a justified regularization parameter in unsupervised domain adaptation. This problem is intriguing as no labels are available in the target domain. Our approach starts with the observation that the widely-used method of minimizing the source error, penalized by a distance measure between source and target feature representations, shares characteristics with regularized ill-posed inverse problems. Regularization parameters in inverse problems are optimally chosen by the fundamental principle of balancing approximation and sampling errors. We use this principle to balance learning errors and domain distance in a target error bound. As a result, we obtain a theoretically justified rule for the choice of the regularization parameter. In contrast to the state of the art, our approach allows source and target distributions with disjoint supports. An empirical comparative study on benchmark datasets underpins the performance of our approach.