ICML 2016poster85 citations

A New PAC-Bayesian Perspective on Domain Adaptation

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Abstract

We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions’ divergence - expressed as a ratio - controls the trade-off between a source error measure and the target voters’ disagreement. Our bound suggests that one has to focus on regions where the source data is informative. From this result, we derive a PAC-Bayesian generalization bound, and specialize it to linear classifiers. Then, we infer a learning algorithm and perform experiments on real data.

BibTeX
@InProceedings{pmlr-v48-germain16,
  title = 	 {A New PAC-Bayesian Perspective on Domain Adaptation},
  author = 	 {Germain, Pascal and Habrard, Amaury and Laviolette, François and Morvant, Emilie},
  booktitle = 	 {Proceedings of The 33rd International Conference on Machine Learning},
  pages = 	 {859--868},
  year = 	 {2016},
  editor = 	 {Balcan, Maria Florina and Weinberger, Kilian Q.},
  volume = 	 {48},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {New York, New York, USA},
  month = 	 {20--22 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v48/germain16.pdf},
  url = 	 {https://proceedings.mlr.press/v48/germain16.html},
  abstract = 	 {We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions’ divergence - expressed as a ratio - controls the trade-off between a source error measure and the target voters’ disagreement. Our bound suggests that one has to focus on regions where the source data is informative. From this result, we derive a PAC-Bayesian generalization bound, and specialize it to linear classifiers. Then, we infer a learning algorithm and perform experiments on real data.}
}