Hypothesis Transfer Learning via Transformation Functions
This work addresses the need for improved theoretical guarantees in transfer learning, offering a domain-specific solution that is incremental in nature.
The paper tackles the Hypothesis Transfer Learning (HTL) problem by proposing a unified framework using transformation functions to relate source and target domains, showing that HTL achieves faster convergence rates for Kernel Smoothing and Kernel Ridge Regression compared to non-transfer learning when domains are related.
We consider the Hypothesis Transfer Learning (HTL) problem where one incorporates a hypothesis trained on the source domain into the learning procedure of the target domain. Existing theoretical analysis either only studies specific algorithms or only presents upper bounds on the generalization error but not on the excess risk. In this paper, we propose a unified algorithm-dependent framework for HTL through a novel notion of transformation function, which characterizes the relation between the source and the target domains. We conduct a general risk analysis of this framework and in particular, we show for the first time, if two domains are related, HTL enjoys faster convergence rates of excess risks for Kernel Smoothing and Kernel Ridge Regression than those of the classical non-transfer learning settings. Experiments on real world data demonstrate the effectiveness of our framework.