Poster
in
Workshop: PAC-Bayes Meets Interactive Learning
PAC-Bayesian Domain Adaptation Bounds for Multi-view learning
Mehdi Hennequin · Khalid Benabdeslem · Haytham Elghazel
Abstract:
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 (Germain et al., 2013; 2015). In this way, we propose an analysis of generalization bounds with Pac-Bayesian theory to consolidate the two paradigms, which are currently treated separately.
Chat is not available.