Agnostic Learning by Refuting

@inproceedings{Kothari2017AgnosticLB,
  title={Agnostic Learning by Refuting},
  author={Pravesh Kothari and Roi Livni},
  year={2017}
}
The sample complexity of learning a Boolean-valued function class is precisely characterized by its Rademacher complexity. This has little bearing, however, on the sample complexity of efficient agnostic learning. We introduce refutation complexity, a natural computational analog of Rademacher complexity of a Boolean concept class and show that it exactly characterizes the sample complexity of efficient agnostic learning. Informally, refutation complexity of a class C is the minimum number of… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 4 times over the past 90 days. VIEW TWEETS