Adaptation Algorithm and Theory Based on Generalized Discrepancy
This work addresses domain adaptation for machine learning applications, but appears incremental as it builds directly on discrepancy minimization.
The authors tackled domain adaptation by developing a new algorithm that improves upon discrepancy minimization, with theoretical guarantees of more favorable learning bounds and experimental results showing it outperforms the previous method.
We present a new algorithm for domain adaptation improving upon a discrepancy minimization algorithm previously shown to outperform a number of algorithms for this task. Unlike many previous algorithms for domain adaptation, our algorithm does not consist of a fixed reweighting of the losses over the training sample. We show that our algorithm benefits from a solid theoretical foundation and more favorable learning bounds than discrepancy minimization. We present a detailed description of our algorithm and give several efficient solutions for solving its optimization problem. We also report the results of several experiments showing that it outperforms discrepancy minimization.