PAC-Bayesian Learning and Domain Adaptation

Pascal Germain (1) , Amaury Habrard (2) , François Laviolette (1) , Emilie Morvant (3, 4, 2)

1 GRAAL
2 LHC - Laboratoire Hubert Curien
3 QARMA - éQuipe AppRentissage et MultimediA [Marseille]
4 LIF - Laboratoire d'informatique Fondamentale de Marseille

In machine learning, Domain Adaptation (DA) arises when the distribution gen- erating the test (target) data differs from the one generating the learning (source) data. It is well known that DA is an hard task even under strong assumptions, among which the covariate-shift where the source and target distributions diverge only in their marginals, i.e. they have the same labeling function. Another popular approach is to consider an hypothesis class that moves closer the two distributions while implying a low-error for both tasks. This is a VC-dim approach that restricts the complexity of an hypothesis class in order to get good generalization. Instead, we propose a PAC-Bayesian approach that seeks for suitable weights to be given to each hypothesis in order to build a majority vote. We prove a new DA bound in the PAC-Bayesian context. This leads us to design the first DA-PAC-Bayesian algorithm based on the minimization of the proposed bound. Doing so, we seek for a ρ-weighted majority vote that takes into account a trade-off between three quantities. The first two quantities being, as usual in the PAC-Bayesian approach, (a) the complexity of the majority vote (measured by a Kullback-Leibler divergence) and (b) its empirical risk (measured by the ρ-average errors on the source sample). The third quantity is (c) the capacity of the majority vote to distinguish some structural difference between the source and target samples.

Mots clés: Domain Adaptation; PAC-Bayes

Domaines: Machine Learning [stat.ML]

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant. PAC-Bayesian Learning and Domain Adaptation. Multi-Trade-offs in Machine Learning, NIPS 2012 Workshop, Dec 2012, Lake Tahoe, United States. ⟨hal-00749366⟩