PAC-Bayesian Domain Adaptation Bounds for Multi-view learning
This work addresses domain adaptation for multi-view learning, an incremental advance that combines two previously separate paradigms to improve theoretical understanding in machine learning.
The paper tackles the problem of domain adaptation in multi-view learning, which had received little prior attention, by introducing a novel distance measure tailored for this setting and providing PAC-Bayesian generalization bounds to analyze it, with comparisons to previous studies.
This paper presents a series of new results for domain adaptation in the multi-view learning setting. The incorporation of multiple views in the domain adaptation was paid little attention in the previous studies. In this way, we propose an analysis of generalization bounds with Pac-Bayesian theory to consolidate the two paradigms, which are currently treated separately. Firstly, building on previous work by Germain et al., we adapt the distance between distribution proposed by Germain et al. for domain adaptation with the concept of multi-view learning. Thus, we introduce a novel distance that is tailored for the multi-view domain adaptation setting. Then, we give Pac-Bayesian bounds for estimating the introduced divergence. Finally, we compare the different new bounds with the previous studies.