Corpus ID: 216144803

A survey on domain adaptation theory

@article{Redko2020ASO,
  title={A survey on domain adaptation theory},
  author={I. Redko and Emilie Morvant and Amaury Habrard and M. Sebban and Youn{\`e}s Bennani},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.11829}
}
All famous machine learning algorithms that correspond to both supervised and semi-supervised learning work well only under a common assumption: training and test data follow the same distribution. When the distribution changes, most statistical models must be reconstructed from new collected data that, for some applications, may be costly or impossible to get. Therefore, it became necessary to develop approaches that reduce the need and the effort of obtaining new labeled samples by exploiting… Expand
Domain adaptation under structural causal models
A Symmetric Loss Perspective of Reliable Machine Learning
Distributional Anchor Regression
Beyond $\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence

References

SHOWING 1-10 OF 81 REFERENCES
On the analysis of adaptability in multi-source domain adaptation
Domain adaptation–can quantity compensate for quality?
Theoretical Analysis of Domain Adaptation with Optimal Transport
A new boosting algorithm for provably accurate unsupervised domain adaptation
Impossibility Theorems for Domain Adaptation
Optimal Transport for Domain Adaptation
Parsimonious unsupervised and semi-supervised domain adaptation with good similarity functions
...
1
2
3
4
5
...