Corpus ID: 232068810

An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization

@article{Rosenfeld2021AnOL,
  title={An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization},
  author={Elan Rosenfeld and Pradeep Ravikumar and Andrej Risteski},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.13128}
}
A popular assumption for out-of-distribution generalization is that the training data comprises subdatasets, each drawn from a distinct distribution; the goal is then to “interpolate” these distributions and “extrapolate” beyond them—this objective is broadly known as domain generalization. A common belief is that ERM can interpolate but not extrapolate and that the latter is considerably more difficult, but these claims are vague and lack formal justification. In this work, we recast… Expand

References

SHOWING 1-10 OF 37 REFERENCES
In Search of Lost Domain Generalization
  • 39
  • PDF
Analysis of Representations for Domain Adaptation
  • 1,066
  • PDF
Domain Generalization via Multidomain Discriminant Analysis
  • 16
  • PDF
Deep Domain Generalization via Conditional Invariant Adversarial Networks
  • 128
  • PDF
Discriminative Learning Under Covariate Shift
  • 243
  • PDF
Regret Bounds for Lifelong Learning
  • 34
  • PDF
Efficient Representations for Lifelong Learning and Autoencoding
  • 42
  • PDF
...
1
2
3
4
...