Approximate Inference via Weighted Rademacher Complexity

@inproceedings{Kuck2018ApproximateIV,
  title={Approximate Inference via Weighted Rademacher Complexity},
  author={Jonathan Kuck and Ashish Sabharwal and Stefano Ermon},
  booktitle={AAAI},
  year={2018}
}
Rademacher complexity is often used to characterize the learnability of a hypothesis class and is known to be related to the class size. We leverage this observation and introduce a new technique for estimating the size of an arbitrary weighted set, defined as the sum of weights of all elements in the set. Our technique provides upper and lower bounds on a novel generalization of Rademacher complexity to the weighted setting in terms of the weighted set size. This generalizes Massart's Lemma, a… CONTINUE READING

References

Publications referenced by this paper.